INDEX

Explanations

quantities and numerical data referenced in the text

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

quantitative durations and quantities

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

 disambiguazione

-0.49

 betweenstory

-0.48

querque

-0.45

AntiForgeryToken

-0.45

mybatisplus

-0.45

 HttpNotFound

-0.43

GLFW

-0.43

">*</

-0.43

jspb

-0.40

ent

-0.39

POSITIVE LOGITS

AndEndTag

0.48

észetes

0.46

eseorang

0.46

 Comprometido

0.45

complexContent

0.44

 HasFactory

0.43

хьтан

0.42

 supérieurs

0.42

 Infórmanos

0.42

 faveur

0.41

Activations Density 0.067%

quantities and numerical data referenced in the text

quantitative durations and quantities

No Comments

No Known Activations