INDEX

Explanations

terms related to programming or code structure, specifically errors and type definitions

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

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

cookieParser

-0.54

 auriculares

-0.49

 jengibre

-0.47

 botines

-0.47

 sélectionnez

-0.47

 sandalias

-0.44

zelfde

-0.44

 calcetines

-0.44

جوايز

-0.44

륙

-0.43

POSITIVE LOGITS

 itſelf

0.71

 لينك

0.67

 leſs

0.63

BibitemShut

0.59

 reaſon

0.58

ⓧ

0.57

 leaſt

0.57

 ſind

0.52

ſelf

0.51

nemia

0.50

Activations Density 0.003%

terms related to programming or code structure, specifically errors and type definitions

No Comments

No Known Activations