INDEX

Explanations

Twitter usernames or handles

oai_token-act-pair · gpt-3.5-turbo

usernames or handles in Twitter posts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 LIMITED

-0.76

 Enabled

-0.73

 diapers

-0.67

 notebooks

-0.66

 fingerprints

-0.66

 Islamists

-0.63

 striking

-0.62

 Lisp

-0.62

 Eighth

-0.62

AFB

-0.61

POSITIVE LOGITS

veyard

0.92

izon

0.88

CBC

0.86

noon

0.85

rentice

0.84

anie

0.83

DonaldTrump

0.82

Anonymous

0.81

news

0.81

official

0.79

Activations Density 0.090%

Twitter usernames or handles

usernames or handles in Twitter posts

No Comments

No Known Activations