INDEX

Explanations

references to food and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 comerciales

-0.51

 kasarigan

-0.47

 کا

-0.45

covite

-0.45

xically

-0.45

 comerciais

-0.44

みると

-0.43

nha

-0.43

رة

-0.43

 Just

-0.43

POSITIVE LOGITS

RenderAtEndOf

0.83

 itſelf

0.77

Efq

0.77

 Theſe

0.73

 faſt

0.73

 myſelf

0.73

 Beſ

0.73

 himſelf

0.72

 whoſe

0.71

 raiſ

0.70

Activations Density 0.301%

references to food and dining experiences

No Comments

No Known Activations