INDEX

Explanations

mathematical expressions and notation involving limits, functions, and variables

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

Fractions and exponents

np_acts-logits-general · gemini-2.0-flash

mathematical notation with exponents and fractions

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

abestanden

-0.57

parsedMessage

-0.57

sizeCache

-0.52

ScopeManager

-0.51

ThroughAttribute

-0.49

 aDecoder

-0.48

getDescriptor

-0.48

intellij

-0.47

 endforeach

-0.47

bibitem

-0.47

POSITIVE LOGITS

partial

0.56

³/

0.55

 €/

0.55

 sancti

0.53

 halves

0.52

thétique

0.52

¼

0.50

resizingMask

0.50

tagHelperRunner

0.50

²/

0.49

Activations Density 1.243%

mathematical expressions and notation involving limits, functions, and variables

Fractions and exponents

mathematical notation with exponents and fractions

No Comments

No Known Activations