INDEX

Explanations

metadata or reference indicators in academic or research documents

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

Captions or descriptions of figures/tables

np_acts-logits-general · gemini-2.0-flash

figures, code, and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

anda

-0.42

 Akad

-0.40

tonode

-0.40

 localObject

-0.40

govina

-0.39

кат

-0.39

/@

-0.38

Dar

-0.38

 Arquivado

-0.37

ெ

-0.36

POSITIVE LOGITS

RenderAtEndOf

0.72

 kasarigan

0.69

BeginContext

0.66

FTFY

0.65

elemField

0.65

MessageTagHelper

0.65

```

0.65

adaptiveStyles

0.64

DockStyle

0.63

دانشنامهٔ

0.63

Activations Density 2.387%

metadata or reference indicators in academic or research documents

Captions or descriptions of figures/tables

figures, code, and technical terms

No Comments

No Known Activations