INDEX

Explanations

terms related to data processing and analysis

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

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

ISupport

-0.62

 déchir

-0.59

 xảy

-0.58

 crainte

-0.57

 scelta

-0.56

 connues

-0.56

 dejen

-0.55

 sonno

-0.55

 connue

-0.55

 colpa

-0.53

POSITIVE LOGITS

 вами

0.90

 мной

0.76

geführten

0.73

 нами

0.72

 тобой

0.72

^(@

0.69

moiselle

0.65

Demografia

0.64

WebElementEntity

0.64

aine

0.64

Activations Density 0.478%

terms related to data processing and analysis

No Comments

No Known Activations