INDEX

Explanations

words indicating temporal progression or sequences of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

gql

-0.39

☚

-0.39

basicConfig

-0.39

queles

-0.38

gls

-0.38

 bookId

-0.37

 primarily

-0.37

stdout

-0.36

あくまで

-0.36

 scolaire

-0.35

POSITIVE LOGITS

Soon

0.73

 Soon

0.70

soon

0.66

ientôt

0.65

 soon

0.64

 Administrativna

0.57

MethodManager

0.56

 muut

0.54

あっという間に

0.53

 CURIAM

0.52

Activations Density 0.016%

words indicating temporal progression or sequences of events

No Comments

No Known Activations