INDEX

Explanations

complex mathematical notations and structures, particularly those involving equations and parameters

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

Characters surrounding mathematical symbols

np_acts-logits-general · gemini-2.0-flash

mathematical and code symbols

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

ORTE

-0.56

تف

-0.54

ab

-0.52

piecze

-0.51

 invokingState

-0.51

ment

-0.51

 esterni

-0.51

 виправивши

-0.50

ēr

-0.50

cheidet

-0.50

POSITIVE LOGITS

PostExecute

0.74

zzleHttp

0.65

ագրություններ

0.63

ModelSerializer

0.63

MENAFN

0.63

ViewInit

0.61

SceneManagement

0.59

phosa

0.56

 truk

0.56

 carats

0.56

Activations Density 0.477%

complex mathematical notations and structures, particularly those involving equations and parameters

Characters surrounding mathematical symbols

mathematical and code symbols

No Comments

No Known Activations