INDEX

Explanations

references to programming functions and buffer operations

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

ngx_buf, assetBundle, oauth2/token

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

-------------</

-0.55

windowFixed

-0.51

scriptcase

-0.49

ViewImports

-0.46

 GenerationType

-0.44

 autorytatywna

-0.43

 виправивши

-0.42

ChildScrollView

-0.42

RegressionTest

-0.41

béco

-0.40

POSITIVE LOGITS

AnchorStyles

0.54

netty

0.52

HandlerContext

0.46

pośred

0.44

featureID

0.42

omentos

0.41

hadores

0.41

tidaknya

0.41

stagland

0.40

 geschlagen

0.40

Activations Density 0.003%

references to programming functions and buffer operations

ngx_buf, assetBundle, oauth2/token

No Comments

No Known Activations