INDEX

Explanations

descriptions related to specific entities, such as "vampire Pam," "American wholesomeness," and "Hollywood hotel."

oai_token-act-pair · gpt-3.5-turbo

references to various cultural and societal stereotypes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 GOODMAN

-0.75

icipated

-0.68

âķĲâķĲ

-0.66

TPPStreamerBot

-0.57

)]

-0.57

imately

-0.56

Ago

-0.53

staking

-0.53

é¾į

-0.53

 sidx

-0.51

POSITIVE LOGITS

eties

0.63

isms

0.60

smanship

0.60

gear

0.58

lon

0.55

vironments

0.55

 outwe

0.55

tones

0.55

stros

0.54

unia

0.53

Activations Density 0.921%

descriptions related to specific entities, such as "vampire Pam," "American wholesomeness," and "Hollywood hotel."

references to various cultural and societal stereotypes

No Comments

No Known Activations