INDEX

Explanations

elements related to data structure or formatting

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

Code or configuration snippets

np_acts-logits-general · gemini-2.0-flash

}}}} closing braces

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 صوتيه

-0.79

RenderAtEndOf

-0.78

 EconPapers

-0.71

AndEndTag

-0.69

EndProject

-0.69

 المعيارى

-0.67

EndGlobalSection

-0.66

MemoryWarning

-0.66

Hozzáférés

-0.66

 كومونز

-0.65

POSITIVE LOGITS

0.49

度

0.43

addPreferredGap

0.42

ärke

0.41

wieś

0.40

 ultime

0.40

 umum

0.39

}}}}

0.39

doin

0.38

bū

0.38

Activations Density 0.026%

elements related to data structure or formatting

Code or configuration snippets

}}}} closing braces

No Comments

No Known Activations