INDEX

Explanations

numerical data and figures within a document

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

.com endings

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

 CreateTagHelper

-0.69

bootstrapcdn

-0.66

 mergeFrom

-0.65

enumii

-0.64

TargetException

-0.63



-0.61

WebElementEntity

-0.60

 NSCoder

-0.59

ագրություններ

-0.59

Tikang

-0.59

POSITIVE LOGITS

 surla

0.43

Style

0.29

 Gleichzeitig

0.29

要

0.29

Zus

0.28

arXiv

0.27

 Stich

0.27

<0x8A>

0.27

 rojas

0.26

Support

0.26

Activations Density 0.191%

numerical data and figures within a document

.com endings

No Comments

No Known Activations