INDEX

Explanations

mentions of various parts and surfaces of objects

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

 vuitton

-0.66

 Normdatei

-0.66

adaptiveStyles

-0.64

 الرياضيه

-0.61

 defaultstate

-0.59

 InputDecoration

-0.57

 querida

-0.56

addCriterion

-0.56

yelitis

-0.55

 AssemblyCulture

-0.53

POSITIVE LOGITS

 portion

1.02

 part

0.98

most

0.95

 section

0.79

部分

0.77

MOST

0.73

portion

0.70

 část

0.66

part

0.66

end

0.64

Activations Density 0.368%

mentions of various parts and surfaces of objects

No Comments

No Known Activations