INDEX

Explanations

mathematical symbols and variables related to formal proofs and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 发表于

-0.49

MathML

-0.49

AddWithValue

-0.44

<?>>

-0.44

 Auss

-0.41

 Unter

-0.41

nonatomic

-0.40

Wea

-0.40

CLAS

-0.40

StackNavigator

-0.39

POSITIVE LOGITS

 للاسماء

1.09

expandindo

0.90

 étoit

0.86

bewerken

0.80

 feroit

0.78

 auroit

0.77

writeFieldEnd

0.76

 Bioaccumulative

0.75

Pozri

0.74

 étoient

0.73

Activations Density 0.709%

mathematical symbols and variables related to formal proofs and definitions

No Comments

No Known Activations