INDEX

Explanations

references to individuals and their experiences or beliefs

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

PerformLayout

-0.66

 <>",

-0.62

δε

-0.55

 AssemblyVersion

-0.53

 ModelExpression

-0.52

ArgumentParser

-0.51

帖最后由

-0.50

pagnol

-0.48

Xna

-0.48

__':

-0.48

POSITIVE LOGITS

who

1.24

 którzy

0.99

 quienes

0.95

who

0.94

 Those

0.85

 kteří

0.84

 those

0.83

 coloro

0.82

Who

0.82

 quien

0.81

Activations Density 0.242%

references to individuals and their experiences or beliefs

No Comments

No Known Activations