INDEX

Explanations

code-related terms and constructs, particularly those related to UI components and event handling

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

Code or special characters

np_acts-logits-general · gemini-2.0-flash

heavy drinkers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eseorang

-0.61

uppertal

-0.53

laces

-0.52

Synonymes

-0.51

 Shreve

-0.50

 CHICAGO

-0.50

SpringBootTest

-0.50

 lakers

-0.49

 Yorkshire

-0.49

 OkHttpClient

-0.49

POSITIVE LOGITS

دانشنامهٔ

0.80

withIdentifier

0.59

 кӀ

0.59

ագրություններ

0.56

parsedMessage

0.54

 ProtoMessage

0.53

mandu

0.53

حياتها

0.52

XmlAccessType

0.52

CPtr

0.51

Activations Density 0.290%

code-related terms and constructs, particularly those related to UI components and event handling

Code or special characters

heavy drinkers

No Comments

No Known Activations