INDEX

Explanations

instances and discussions related to women

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 purpoſe

-0.81

 Cæsar

-0.79

 Theſe

-0.78

 pleaſure

-0.77

 himſelf

-0.76

 iſt

-0.75

 Monfieur

-0.74

 Majefty

-0.74

 itſelf

-0.71

 myſelf

-0.71

POSITIVE LOGITS

 woman

3.03

 women

2.76

 Woman

2.71

Woman

2.61

woman

2.57

 Women

2.52

women

2.46

Women

2.43

 WOMAN

2.36

 WOMEN

2.23

Activations Density 0.117%

instances and discussions related to women

No Comments

No Known Activations