INDEX

Explanations

mentions of the name "Tom."

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

Following "Tom"

np_acts-logits-general · gemini-2.0-flash

Tom followed by another capitalized word

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.65

ंदीखरीदारी

-0.58

 ProtoMessage

-0.57

XmlAccessorType

-0.56

Anhalt

-0.54

aarrggbb

-0.53

 ModelExpression

-0.53

AnchorStyles

-0.52

ollectionView

-0.52

postsleuth

-0.51

POSITIVE LOGITS

atoes

0.75

ORROW

0.74

Tom

0.69

 Aquinas

0.64

tom

0.63

 raider

0.62

pkins

0.60

 CURIAM

0.56

findpost

0.56

Tom

0.55

Activations Density 0.080%

mentions of the name "Tom."

Following "Tom"

Tom followed by another capitalized word

No Comments

No Known Activations