INDEX

Explanations

dates or specific numerical sequences

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or geographical areas

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

ificial

-0.62

angelo

-0.62

ulhu

-0.60

taboola

-0.59

nces

-0.57

zona

-0.55

ccording

-0.54

Cola

-0.54

 ACTIONS

-0.53

arth

-0.53

POSITIVE LOGITS

schild

0.70

 Hutch

0.59

ansk

0.57

Esk

0.57

oice

0.57

pees

0.57

tein

0.55

iland

0.55

owship

0.54

ONSORED

0.54

Activations Density 1.218%

dates or specific numerical sequences

references to specific locations or geographical areas

No Comments

No Known Activations