INDEX

Explanations

numerical representations, likely related to mathematical or programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 World

-0.57

AnchorStyles

-0.53

 National

-0.53

 fully

-0.52

we

-0.51

Sha

-0.51

決して

-0.50

 most

-0.49

not

-0.49

 national

-0.49

POSITIVE LOGITS

contentLoaded

1.00

 AssemblyProduct

0.91

NewUrlParser

0.88

 فريبيس

0.87

 propOrder

0.86

 HttpNotFound

0.81

EDEFAULT

0.80

ⓧ

0.80

دانشنامهٔ

0.79

IVEREF

0.79

Activations Density 0.428%

numerical representations, likely related to mathematical or programming concepts

No Comments

No Known Activations