INDEX

Explanations

words related to politics and government

oai_token-act-pair · gpt-3.5-turbo

references to names, organizations, and items related to sports and research

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

ournals

-0.66

 camel

-0.52

 Aram

-0.49

 slump

-0.48

ilyn

-0.47

 cour

-0.46

 Pixar

-0.46

amar

-0.46

MAC

-0.46

 tails

-0.46

POSITIVE LOGITS

ibrary

0.70

abulary

0.60

overe

0.60

achev

0.60

henko

0.57

ombat

0.57

lycer

0.57

ãĥĺãĥ©

0.55

QL

0.55

gage

0.53

Activations Density 1.043%

words related to politics and government

references to names, organizations, and items related to sports and research

No Comments

No Known Activations