INDEX

Explanations

technical or code-related terms and symbols related to various programming languages

oai_token-act-pair · gpt-3.5-turbo

references to health-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ratom

-0.58

DCS

-0.54

 Fallout

-0.49

 Fault

-0.48

 Tycoon

-0.48

 Faces

-0.46

NBN

-0.46

 Bitcoin

-0.45

 Combine

-0.45

 partName

-0.45

POSITIVE LOGITS

çĶ°

0.76

cellaneous

0.63

idia

0.62

«

0.60

ī

0.59

cffffcc

0.58

é¾įåĸļå£«

0.57

otal

0.57

ħ

0.57

razil

0.56

Activations Density 0.420%

technical or code-related terms and symbols related to various programming languages

references to health-related topics

No Comments

No Known Activations