INDEX

Explanations

words indicating age and gender

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

dv

-0.59

出版年

-0.59

съ

-0.58

въ

-0.57

chaus

-0.56

Väl

-0.56

 Tran

-0.55

繁

-0.55

usehen

-0.54

vš

-0.54

POSITIVE LOGITS

Efq

0.99

 Jefus

0.84

 Monfieur

0.80

toMatchSnapshot

0.79

 myſelf

0.78

 holotype

0.78

PMailer

0.77

 whoſe

0.75

 betweenstory

0.74

mergeFrom

0.73

Activations Density 0.100%

words indicating age and gender

No Comments

No Known Activations