INDEX

Explanations

gender-specific possessive pronouns

oai_token-act-pair · gpt-3.5-turbo

references to women's categories or events

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

mr

-0.83

uncle

-0.79

hiba

-0.77

hari

-0.75

Reviewer

-0.74

leased

-0.73

cedented

-0.71

ciating

-0.70

ific

-0.70

osponsors

-0.70

POSITIVE LOGITS

 International

0.74

 Caucus

0.74

 Cooper

0.72

 rights

0.70

 participation

0.69

 Liberation

0.69

 pursuit

0.68

 clubs

0.68

 Crusade

0.68

istance

0.66

Activations Density 0.053%

gender-specific possessive pronouns

references to women's categories or events

No Comments

No Known Activations