INDEX

Explanations

names of specific individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals and entities

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

spring

-0.85

respons

-0.76

ename

-0.75

ceed

-0.72

juven

-0.71

raising

-0.71

uate

-0.70

 Crusader

-0.70

oral

-0.70

eatures

-0.70

POSITIVE LOGITS

 Wheeler

0.89

\\\\\\\\

0.86

Wheel

0.78

HEAD

0.71

inson

0.70

Merit

0.70

andowski

0.68

 shred

0.68

pad

0.68

leigh

0.67

Activations Density 0.025%

names of specific individuals

proper nouns, specifically names of individuals and entities

No Comments

No Known Activations