INDEX

Explanations

components and references related to a specific programming framework

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

legal citations and document references

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

aarrggbb

-0.78

 estekak

-0.76

RenderAtEndOf

-0.73

UrlResolution

-0.72

 InputDecoration

-0.71

Datuak

-0.70

LLocation

-0.68

WireFormatLite

-0.67

 насељу

-0.66

 snippetHide

-0.65

POSITIVE LOGITS

 MediatR

0.40

년

0.37

 Super

0.36

PageFactory

0.34

flex

0.33

 butterknife

0.33

 principle

0.32

Super

0.32

 doctrina

0.30

 super

0.30

Activations Density 0.018%

components and references related to a specific programming framework

legal citations and document references

No Comments

No Known Activations