INDEX

Explanations

mention the last names or names of certain individuals

oai_token-act-pair · gpt-3.5-turbo

words and names associated with people or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 clipboard

-0.73

 Brist

-0.73

 therape

-0.72

 Cassandra

-0.72

 Lionel

-0.69

 Hanna

-0.66

 Benz

-0.65

 ankles

-0.64

 grading

-0.64

 hairst

-0.63

POSITIVE LOGITS

1.36

uin

1.26

uci

1.19

uid

1.18

uv

1.17

uc

1.17

Å«

1.14

uni

1.11

uf

1.10

ulk

1.09

Activations Density 0.172%

mention the last names or names of certain individuals

words and names associated with people or characters

No Comments

No Known Activations