INDEX

Explanations

numeric values and their associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

tagHelperRunner

-0.87

LookAnd

-0.83

 חיצוניים

-0.81

 intptr

-0.75

 createSlice

-0.75

Дереккөздер

-0.72

ScopeManager

-0.68

 AssemblyProduct

-0.68

دانشنامهٔ

-0.67

AddHtmlAttribute

-0.65

POSITIVE LOGITS

 kasarigan

0.53

 Arkivert

0.52

 Maho

0.52

 nuns

0.50

 Faro

0.49

 exile

0.49

vertebrates

0.47

 Sima

0.46

usermodel

0.46

phe

0.46

Activations Density 0.646%

numeric values and their associations

No Comments

No Known Activations