INDEX

Explanations

elements of code or data structure definitions involving objects and entries

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

code structure and symbols

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

 TextInputType

-0.63

 ProtoMessage

-0.59

 ivelany

-0.57

expandindo

-0.53

Espèce

-0.51

 GenerationType

-0.49

 OMITBAD

-0.48

IntoConstraints

-0.47

EDEFAULT

-0.46

createCanvas

-0.45

POSITIVE LOGITS

 فريبيس

0.44

writerow

0.44

ambilan

0.41

 informée

0.40

berdayakan

0.39

antaranya

0.39

 Inscrivez

0.39

representing

0.39

 représentant

0.38

 puffs

0.38

Activations Density 0.118%

elements of code or data structure definitions involving objects and entries

code structure and symbols

No Comments

No Known Activations