INDEX

Explanations

references to comprehensive resources or guides

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

脚注の使い方

-0.97

TypedDataSet

-0.85

contentLoaded

-0.84

ագրություններ

-0.83

abestanden

-0.81

AsUp

-0.80

Geplaatst

-0.80

InitVars

-0.80

出版年

-0.79

ThroughAttribute

-0.76

POSITIVE LOGITS

 special

0.78

 online

0.72

 interactive

0.70

 series

0.67

 comprehensive

0.64

new

0.62

 FREE

0.62

 monthly

0.60

 speciale

0.59

interactive

0.58

Activations Density 0.283%

references to comprehensive resources or guides

No Comments

No Known Activations