INDEX

Explanations

references to physical locations such as a booth

oai_token-act-pair · gpt-3.5-turbo

mentions of "booth" in various contexts

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

mitted

-0.79

ochond

-0.78

itals

-0.77

rises

-0.76

cens

-0.74

ths

-0.73

hed

-0.73

inse

-0.69

":"/

-0.67

andals

-0.65

POSITIVE LOGITS

holders

0.95

 booth

0.94

holder

0.90

 booths

0.85

swer

0.78

Lens

0.73

handler

0.72

SourceFile

0.70

Ħ¢

0.68

wagon

0.68

Activations Density 0.042%

references to physical locations such as a booth

mentions of "booth" in various contexts

No Comments

No Known Activations