INDEX

Explanations

mentions of readers or readership

oai_token-act-pair · gpt-3.5-turbo

references to 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

rament

-0.86

ering

-0.85

 corrid

-0.74

eton

-0.71

remlin

-0.68

ela

-0.67

apes

-0.66

equality

-0.66

gypt

-0.65

apeake

-0.65

POSITIVE LOGITS

boys

0.84

 Supported

0.79

 Reader

0.79

 extraord

0.78

="#

0.75

boy

0.75

idge

0.72

gate

0.72

 APPLIC

0.71

sonian

0.70

Activations Density 0.033%

mentions of readers or readership

references to the reader or audience

No Comments

No Known Activations