INDEX

Explanations

references to specific entities, particularly related to items, concepts, or terms that begin with the letter "J."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 måte

-0.59

 operativos

-0.58

帖最后由

-0.57

köy

-0.55

 LCCN

-0.55

 corrector

-0.55

 règle

-0.54

setAll

-0.53

 Procu

-0.53

 occaf

-0.53

POSITIVE LOGITS

 Jamb

0.72

Jop

0.71

Jow

0.69

 JSTOR

0.68

 Jara

0.67

 jsonArray

0.65

 Jill

0.64

JPM

0.64

JAS

0.64

Jav

0.64

Activations Density 0.717%

references to specific entities, particularly related to items, concepts, or terms that begin with the letter "J."

No Comments

No Known Activations