INDEX

Explanations

references to specific individuals or names, often related to music or cultural content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 émotions

-0.57

igshid

-0.56

참고

-0.54

 réflex

-0.53

飽

-0.50

errHandler

-0.50

addCriterion

-0.49

 personnalité

-0.48

 culte

-0.48

 emozioni

-0.48

POSITIVE LOGITS

 Irish

0.87

 Irishman

0.80

Irish

0.76

 Murphy

0.71

herty

0.71

 irish

0.70

 McCarthy

0.70

 Conor

0.68

 Ireland

0.68

Activations Density 0.207%

references to specific individuals or names, often related to music or cultural content

No Comments

No Known Activations