INDEX

Explanations

concepts related to repetition and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AutoScaleMode

-0.62

 JpaRepository

-0.53

 ThemeData

-0.51

illus

-0.49

GIVEREF

-0.49

cektir

-0.49

endregion

-0.48

mixin

-0.47

||

-0.47

 nourrir

-0.45

POSITIVE LOGITS

Sucesor

0.63

typeorm

0.62

 again

0.60

bewerken

0.60

 recommen

0.59

 tartalomajánló

0.59

 fresher

0.57

ensement

0.57

 newData

0.57

 afresh

0.57

Activations Density 0.319%

concepts related to repetition and processes

No Comments

No Known Activations