INDEX

Explanations

references to specific individuals or prior work in the context of research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

LookAnd

-0.89

 nahilalakip

-0.87

 مرئيه

-0.75

 مشين

-0.72

 ISNI

-0.70

حياته

-0.70



-0.69

anho

-0.69

Билгалдахарш

-0.65

 therefrom

-0.65

POSITIVE LOGITS

 preceding

0.70

 fixture

0.67

?";

0.65

expandindo

0.58

ConstraintMaker

0.56

igi

0.55

 Hunters

0.53

yks

0.53

 Berg

0.52

 syndrome

0.52

Activations Density 0.047%

references to specific individuals or prior work in the context of research

No Comments

No Known Activations