INDEX

Explanations

HTML comment markers

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

HTML comments

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

 MainAxisSize

-0.56

出版年

-0.51

 pleaſure

-0.50

Général

-0.45

+#+#

-0.45

bufio

-0.45

 виправивши

-0.45

PhysRevD

-0.44

SpringRunner

-0.43

tvguidetime

-0.43

POSITIVE LOGITS

<!--

1.55

 <!--

1.11

><!--

1.05

"><!--

0.86

/*

0.81

<!--

0.81

{/*

0.78

__(/*!

0.75

/**

0.75

//

0.71

Activations Density 0.007%

HTML comment markers

HTML comments

No Comments

No Known Activations