INDEX

Explanations

nested structure elements within code snippets

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

code structuring elements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Kitch

-0.38

上一

-0.35

einf

-0.34

bon

-0.33

emb

-0.33

чье

-0.32

 disambiguazione

-0.32

WindowEvent

-0.31

genheim

-0.30

 MwSt

-0.30

POSITIVE LOGITS

/**

0.79

BibitemShut

0.64

rungsseite

0.63

 JpaRepository

0.59

findpost

0.55



0.53

 desmotivaciones

0.53

pulseira

0.53

TabIndex

0.53

enderror

0.52

Activations Density 0.003%

nested structure elements within code snippets

code structuring elements

No Comments

No Known Activations