INDEX

Explanations

programming code and syntax elements

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

references and 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

drawSprites

-0.39

itattu

-0.35

 viewDidLoad

-0.33

ᅠ

-0.33

Jeografia

-0.32

 kaarangay

-0.30

classnames

-0.29

Hozzáférés

-0.29

ttemberg

-0.28

AddAttribute

-0.28

POSITIVE LOGITS

tagHelperRunner

0.66

 <<<<<<<<<<<<<<

0.65

 ſch

0.56

 ſtate

0.56

✨:

0.54

issex

0.54

BeginContext

0.52

前から

0.52

évaluateur

0.52

 viſ

0.51

Activations Density 0.109%

programming code and syntax elements

references and comments

No Comments

No Known Activations