INDEX

Explanations

references to specific individuals and their actions or characteristics

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

chappement

-0.33

 Pflicht

-0.33

uramente

-0.33

Requirement

-0.32

 gema

-0.32

 emploi

-0.31

 '=',

-0.31

 dores

-0.30

 Paix

-0.29

 verw

-0.29

POSITIVE LOGITS

oneofs

0.70

rungsseite

0.66

 nahilalakip

0.63

BuildContext

0.63

sizeCache

0.62

expandindo

0.61

PYX

0.59

帖最后由

0.57

 ویکی‌پدی

0.57

tagHelperRunner

0.56

Activations Density 0.085%

references to specific individuals and their actions or characteristics

No Comments

No Known Activations