INDEX

Explanations

terms relating to societal and political issues, particularly focusing on feminist and leftist discourse

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 وتسجيلات

-0.44

createStatement

-0.44

ECONDS

-0.44

 lasse

-0.43

 fré

-0.43

ophosph

-0.42

 orthon

-0.41

 rech

-0.41

 Fieber

-0.41

 vektor

-0.40

POSITIVE LOGITS

 women

0.97

 sexist

0.95

 sexism

0.93

 female

0.89

 females

0.88

 gender

0.87

 Women

0.86

 feminist

0.85

 feminists

0.83

Women

0.82

Activations Density 1.075%

terms relating to societal and political issues, particularly focusing on feminist and leftist discourse

No Comments

No Known Activations