INDEX

Explanations

structured data or information formatted in a specific way

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 iſt

-0.81

 ―――――

-0.79

 sánchez

-0.78

 faſt

-0.74

 ſche

-0.72

nú

-0.71

 CHAPITRE

-0.70

 staffel

-0.68

ly

-0.68

 pegat

-0.68

POSITIVE LOGITS

1.03

zkopf

0.73

}{*}{}

0.72

󠁿

0.71

↵

0.65

フェクト

0.64

 vastaan

0.63

</em>

0.62

ség

0.62

 Audiodateien

0.62

Activations Density 0.003%

structured data or information formatted in a specific way

No Comments

No Known Activations