INDEX

Explanations

references to political figures with the title "Speaker."

oai_token-act-pair · gpt-3.5-turbo

mentions of political roles or titles, specifically "Speaker."

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

ibaba

-0.75

eros

-0.73

schild

-0.72

kus

-0.69

kinson

-0.66

 sled

-0.66

ter

-0.65

tera

-0.61

erial

-0.60

pend

-0.60

POSITIVE LOGITS

 Speaker

0.88

 speaker

0.85

ħĭ

0.78

 Newt

0.77

person

0.76

loo

0.75

llor

0.73

 Gingrich

0.72

sonian

0.71

woman

0.71

Activations Density 0.014%

references to political figures with the title "Speaker."

mentions of political roles or titles, specifically "Speaker."

No Comments

No Known Activations