INDEX

Explanations

proper names (often related to famous individuals) or keywords such as "recipe", "cafe", "performance", and "horror film"

oai_token-act-pair · gpt-3.5-turbo

the presence of certain names and terms, particularly those related to Australian culture or context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lehem

-0.72

 fines

-0.71

 grandchildren

-0.63

aez

-0.62

 setbacks

-0.62

cause

-0.62

ibles

-0.60

rosso

-0.60

 acute

-0.60

uously

-0.59

POSITIVE LOGITS

velt

0.99

 Rampage

0.78

heid

0.77

 Janeiro

0.74

lund

0.70

kefeller

0.68

estern

0.68

Unix

0.68

restling

0.66

phant

0.65

Activations Density 0.128%

proper names (often related to famous individuals) or keywords such as "recipe", "cafe", "performance", and "horror film"

the presence of certain names and terms, particularly those related to Australian culture or context

No Comments

No Known Activations