INDEX

Explanations

programming syntax and structure

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

Code, symbols, and uncommon words

np_acts-logits-general · gemini-2.0-flash

code, programming, and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 resourceCulture

-0.80

 prediction

-0.78

 חיצוניים

-0.76

 Predict

-0.75

 ModelExpression

-0.75

 predictions

-0.73

 Prediction

-0.73

 समीक्षाएं

-0.73

 predict

-0.71

 Predictions

-0.71

POSITIVE LOGITS

хьтан

0.52

yntaxException

0.47

NSIndexPath

0.46

JAKARTA

0.45

 chinoise

0.45

 đạp

0.44

UML

0.44

AFN

0.44

XtraBars

0.44

helves

0.43

Activations Density 0.157%

programming syntax and structure

Code, symbols, and uncommon words

code, programming, and technical terms

No Comments

No Known Activations