INDEX

Explanations

names of locations and titles with a focus on criminal activities

oai_token-act-pair · gpt-3.5-turbo

proper nouns and significant entities within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

•Partition Features Layer 8 GPT2 Small

" token" vs "token"

•Induction Feature

No Comments

Negative Logits

ALS

-0.88

 Unch

-0.88

 acknow

-0.88

Pes

-0.84

IB

-0.79

MIS

-0.79

IPM

-0.78

 estab

-0.78

 thous

-0.76

 Antar

-0.75

POSITIVE LOGITS

shop

1.39

organ

1.39

run

1.39

floor

1.38

part

1.37

move

1.37

do

1.36

free

1.35

max

1.34

mist

1.33

Activations Density 0.389%

names of locations and titles with a focus on criminal activities

proper nouns and significant entities within the text

No Comments

No Known Activations