INDEX

Explanations

questions directed towards the reader

oai_token-act-pair · gpt-3.5-turbo

questions directed at the reader or audience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Pierre

-0.71

åħī

-0.71

bats

-0.66

Leaks

-0.66

bang

-0.65

responsible

-0.65

VICE

-0.64

Domain

-0.63

CEPT

-0.63

SHIP

-0.62

POSITIVE LOGITS

 been

0.95

 Entered

0.91

been

0.90

 Been

0.89

 undergone

0.85

 gotten

0.79

 fallen

0.77

 lately

0.76

 mastered

0.75

 kindly

0.74

Activations Density 0.058%

questions directed towards the reader

questions directed at the reader or audience

No Comments

No Known Activations