INDEX

Explanations

references to gender or sex-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-1.02

orteur

-0.96

 Amon

-0.88

matchCondition

-0.88

 Baillargeon

-0.88

UserScript

-0.87

RepeatedField

-0.85

 delantera

-0.83

ization

-0.83

 serializers

-0.82

POSITIVE LOGITS

quate

0.86

sex

0.73

Sex

0.71

 Mund

0.66

das

0.66

 Kath

0.65

 dada

0.64

 Dudley

0.64

Kath

0.62

cos

0.62

Activations Density 0.104%

references to gender or sex-related topics

No Comments

No Known Activations