INDEX

Explanations

references to notable events, figures, and elements in historical or cultural 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

UnusedPrivate

-0.79

ForValue

-0.66

 للمعارف

-0.65

 tantôt

-0.63

évaluateur

-0.61

 sélectionnés

-0.60

 OnInit

-0.60

 فريبيس

-0.59

 useStyles

-0.58

󠁿

-0.57

POSITIVE LOGITS

 significant

1.47

 meaningful

1.30

 major

1.21

 viable

1.20

 serious

1.20

 appreciable

1.15

 decent

1.13

 truly

1.11

 meaningfully

1.07

 substantial

1.07

Activations Density 0.948%

references to notable events, figures, and elements in historical or cultural contexts

No Comments

No Known Activations