INDEX

Explanations

names of individuals in leadership or official positions

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

Attribution of statements

np_acts-logits-general · gemini-2.0-flash

reporting verbs and discourse markers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 виправивши

-0.93

 ModelExpression

-0.84

Hochspringen

-0.75

LEncoder

-0.72

ngrx

-0.71

IBOutlet

-0.67

Portály

-0.66

 wikipagina

-0.63

 JpaRepository

-0.61

 contemporain

-0.61

POSITIVE LOGITS

 said

0.69

 further

0.59

 urged

0.54

 furthermore

0.53

 also

0.52

 inoltre

0.51

op

0.50

 claimed

0.50

 asked

0.50

 moreover

0.48

Activations Density 0.134%

names of individuals in leadership or official positions

Attribution of statements

reporting verbs and discourse markers

No Comments

No Known Activations