INDEX

Explanations

documentation-related terms and markup elements

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

ismet

-0.47

 front

-0.44

:^(

-0.42

 Bear

-0.41

hending

-0.41

Ӕ

-0.41

‡

-0.40

 bear

-0.40

кновен

-0.39

miso

-0.39

POSITIVE LOGITS

 للاسماء

1.14

 فريبيس

0.80

 InputDecoration

0.74

RectangleBorder

0.74

 régle

0.71

verwijspagina

0.70

featureID

0.69



0.68

 defStyleAttr

0.66

IntoConstraints

0.66

Activations Density 0.014%

documentation-related terms and markup elements

No Comments

No Known Activations