INDEX

Explanations

Twitter handles in text data

oai_token-act-pair · gpt-3.5-turbo

mentions of the platform Twitter

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Duff

-0.70

ailability

-0.68

 Sakuya

-0.63

 bliss

-0.62

Vie

-0.62

 Samoa

-0.62

 Wonderland

-0.61

 volunt

-0.61

 Goldberg

-0.61

CPR

-0.60

POSITIVE LOGITS

twitter

1.19

doi

0.85

cdn

0.83

://

0.83

externalActionCode

0.81

(@

0.73

wik

0.73

youtu

0.73

âĢİ

0.70

dp

0.70

Activations Density 0.009%

Twitter handles in text data

mentions of the platform Twitter

No Comments

No Known Activations