INDEX

Explanations

sequences of specific data structures or formatting in technical texts

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

greatest common factor or divisor

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RenderAtEndOf

-0.78

 tartalomajánló

-0.66

writeFieldEnd

-0.66

Autoritní

-0.66

 виправивши

-0.63

 otomatig

-0.62

 الحره

-0.61

 informée

-0.60

出版年

-0.59

httphttps

-0.59

POSITIVE LOGITS

 frontal

0.32

zystać

0.29

 escuchado

0.29

 unacc

0.29

 currently

0.28

Espèce

0.28

 Frontal

0.28

 konk

0.27

setProduct

0.26

 recently

0.26

Activations Density 0.035%

sequences of specific data structures or formatting in technical texts

greatest common factor or divisor

No Comments

No Known Activations