INDEX

Explanations

references to music and songs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 nonatomic

-0.63

 caduta

-0.57

 luck

-0.56

 désol

-0.56

 melden

-0.55

 pioggia

-0.55

 insuffisamment

-0.55

 effray

-0.54

UserScript

-0.54

 côtes

-0.54

POSITIVE LOGITS

 songs

0.95

 scent

0.89

 propOrder

0.89

 song

0.84

 CURIAM

0.77

 smoking

0.76

 scents

0.75

endregion

0.74

windowFixed

0.73

 music

0.72

Activations Density 0.107%

references to music and songs

No Comments

No Known Activations