INDEX

Explanations

words related to a specific female character named "her" or pronouns indicating her

oai_token-act-pair · gpt-3.5-turbo

references to a specific individual, suggesting focus on personal narratives or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

•female

No Comments

Negative Logits

ypes

-0.99

ype

-0.99

ornia

-0.82

kefeller

-0.78

arios

-0.75

isco

-0.69

anamo

-0.69

ollo

-0.69

hovah

-0.68

undo

-0.67

POSITIVE LOGITS

 husband

1.50

ding

1.32

cule

1.29

metic

1.25

 herself

1.16

 boyfriend

1.10

ded

1.09

nia

1.06

 daughter

1.06

 Majesty

1.04

Activations Density 0.136%

words related to a specific female character named "her" or pronouns indicating her

references to a specific individual, suggesting focus on personal narratives or achievements

No Comments

No Known Activations