INDEX

Explanations

terms related to public affairs or public entities

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

following "Public"

np_acts-logits-general · gemini-2.0-flash

public followed by domain

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

InjectAttribute

-0.81

AccessorTable

-0.79

memoized

-0.74

Демографія

-0.73

出版年

-0.72

Hochspringen

-0.71

AndEndTag

-0.70

 kaarangay

-0.69

ValueStyle

-0.69

mergeFrom

-0.69

POSITIVE LOGITS

 opinion

0.72

ally

0.72

 sector

0.70

 domain

0.69

domain

0.65

 health

0.65

 relations

0.59

sector

0.55

 Works

0.54

 Domain

0.53

Activations Density 0.062%

terms related to public affairs or public entities

following "Public"

public followed by domain

No Comments

No Known Activations