INDEX

Explanations

references to programming constructs, especially involving files and image-related functionalities

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

programming constructs and file paths

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

 kysy

-0.44

expandindo

-0.44

Baden

-0.43

utentic

-0.42

 BoxFit

-0.42

bootstrapcdn

-0.42

 jadx

-0.41

Identity

-0.41

posições

-0.41

 yerine

-0.40

POSITIVE LOGITS

@"/

1.71

typeorm

1.44

ConverterFactory

1.11

initState

0.86

VIAF

0.81

ModelForm

0.81

 VIAF

0.76

 HasFactory

0.72

Scaler

0.70

OGND

0.69

Activations Density 0.002%

references to programming constructs, especially involving files and image-related functionalities

programming constructs and file paths

No Comments

No Known Activations

references to programming constructs, especially involving files and image-related functionalities

programming constructs and file paths

No Comments

No Known Activations