INDEX

Explanations

statements made by individuals

oai_token-act-pair · gpt-3.5-turbo

statements attributed to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

irrel

-0.73

poon

-0.70

aceae

-0.66

pmwiki

-0.65

ãĥİ

-0.64

SourceFile

-0.64

aph

-0.63

tyard

-0.63

bang

-0.63

pee

-0.63

POSITIVE LOGITS

 that

1.18

that

0.86

0.83

 furthermore

0.80

adays

0.78

 there

0.77

 governments

0.72

:"

0.72

:]

0.72

 policymakers

0.70

Activations Density 0.208%

statements made by individuals

statements attributed to individuals

No Comments

No Known Activations