INDEX

Explanations

references to features and their manipulation in data analysis contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

astify

-0.59

BoxShadow

-0.56

Mow

-0.53

 bocca

-0.53

 Schnitt

-0.52

NullException

-0.51

 Martini

-0.51

 cappello

-0.50

йтинг

-0.50

zelf

-0.50

POSITIVE LOGITS

 ModelExpression

0.98

PerformLayout

0.84

 typelib

0.74

Personendaten

0.73

 propOrder

0.71

 disambiguazione

0.71

rungsseite

0.70

 AspNetCore

0.69

 виправивши

0.68

ViewFeatures

0.65

Activations Density 1.267%

references to features and their manipulation in data analysis contexts

No Comments

No Known Activations