INDEX

Explanations

conditional phrases and expressions of opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

󠁴

-0.84

QMetaType

-0.76

ronpa

-0.73

riors

-0.68

יוחד

-0.66

UrlResolution

-0.66

ImageContext

-0.64

rophes

-0.63

autaire

-0.63

률

-0.62

POSITIVE LOGITS

Skocz

0.58

 nakalista

0.53

 irony

0.49

 guess

0.49

)).

0.48

fort

0.48

х

0.48

ゴ

0.48

um

0.48

You

0.46

Activations Density 0.496%

conditional phrases and expressions of opinion

No Comments

No Known Activations