INDEX

Explanations

metadata and publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 kasarigan

-0.72

 للاسماء

-0.71

DMETHOD

-0.49

省市镇

-0.49

tagHelperRunner

-0.48

 հղումներ

-0.44

Parcelize

-0.44

 فريبيس

-0.44

tonode

-0.43

expandindo

-0.43

POSITIVE LOGITS

SourceChecksum

0.47

who

0.45

addCriterion

0.42

ScopeManager

0.42

 którzy

0.42

+#+

0.42

 GetEnumerator

0.41

arangay

0.41

 tarafından

0.38

 kteří

0.37

Activations Density 0.789%

metadata and publication details

No Comments

No Known Activations