INDEX

Explanations

references to statistical metrics or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

cze

-0.75

adpleegd

-0.73

 Eugenia

-0.72

 Humphreys

-0.70

 Coulter

-0.69

 purpoſe

-0.69

anni

-0.69

الحياه

-0.69

Dae

-0.69

 defire

-0.68

POSITIVE LOGITS

2.35

2.19

getR

1.42

Ｒ

1.17

fR

1.14

mR

1.13

1.03

dR

1.01

ر

0.93

aR

0.92

Activations Density 0.258%

references to statistical metrics or results

No Comments

No Known Activations