INDEX

Explanations

references to academic journals and scientific publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Sne

-0.42

prevState

-0.40

getElementById

-0.40

jica

-0.39

fattning

-0.39

盤

-0.39

Халык

-0.38

 termin

-0.38

 sunset

-0.38

POV

-0.37

POSITIVE LOGITS

volume

0.81

 estekak

0.76

UnsafeEnabled

0.76

 Volume

0.74

 volume

0.73

expandindo

0.73

vol

0.72

 sqlSession

0.72

Volume

0.72

VersionUID

0.70

Activations Density 0.250%

references to academic journals and scientific publications

No Comments

No Known Activations