INDEX

Explanations

statements or quotes attributed to various well-known individuals

oai_token-act-pair · gpt-3.5-turbo

phrases involving declarations or statements made by influential figures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ept

-0.63

wx

-0.62

zens

-0.62

generated

-0.61

\/\/

-0.60

lette

-0.60

EDIT

-0.60

olar

-0.59

antine

-0.59

allery

-0.58

POSITIVE LOGITS

 famously

0.83

 bluntly

0.76

è¦ļéĨĴ

0.74

 aloud

0.73

 unequivocally

0.72

 farewell

0.72

 himself

0.71

 explicitly

0.69

 encour

0.68

peak

0.67

Activations Density 0.416%

statements or quotes attributed to various well-known individuals

phrases involving declarations or statements made by influential figures

No Comments

No Known Activations