INDEX

Explanations

mentions of the name "Tom" or variations of it in the text

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

Tom

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

DataAnnotations

-0.59

encils

-0.56

arelli

-0.50

bleed

-0.49

bibfield

-0.48

gulier

-0.48

 />';

-0.48

equilibrium

-0.47

 betweenstory

-0.47

 culturelle

-0.47

POSITIVE LOGITS

Tom

0.96

Tom

0.91

TOM

0.83

tom

0.80

 Toms

0.78

TOM

0.75

tom

0.74

 tomes

0.64

Tomo

0.64

tomo

0.63

Activations Density 0.010%

mentions of the name "Tom" or variations of it in the text

Tom

No Comments

No Known Activations