INDEX

Explanations

references to themes in various contexts

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

akei

-0.53

 noqa

-0.52

 OMITBAD

-0.51

 elettron

-0.51

aneo

-0.49

isy

-0.48

ap

-0.47

drawText

-0.47

 leggi

-0.46

 proof

-0.45

POSITIVE LOGITS

 themes

1.16

themes

1.09

 Themes

1.00

Themes

0.98

THEME

0.97

 Theme

0.96

 theme

0.90

 THEME

0.85

theme

0.80

 thème

0.78

Activations Density 0.053%

references to themes in various contexts

No Comments

No Known Activations