INDEX

Explanations

references to scientific articles and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 coreana

-0.65

ImageContext

-0.60

 florales

-0.58

клопе

-0.57

 darbu

-0.57

,:);

-0.56

Açık

-0.56

 smlou

-0.54

 HttpNotFound

-0.54

 abbraccio

-0.52

POSITIVE LOGITS

Referencies

0.63

 متعلقه

0.56

unhofer

0.55

elemField

0.55

henswürdigkeiten

0.54

!*\

0.53

strum

0.51

↵↵↵

0.51

Sucesor

0.51

참고

0.50

Activations Density 0.136%

references to scientific articles and publications

No Comments

No Known Activations