INDEX

Explanations

mathematical expressions and equations

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

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

 defaultstate

-0.46

 لات

-0.44

Ran

-0.43

 وتسجيلات

-0.41

phrine

-0.41

Die

-0.40

TestClass

-0.40

Ran

-0.40

Pautan

-0.40

ryn

-0.39

POSITIVE LOGITS

:✨

0.98

 twice

0.97

 Twice

0.85

twice

0.85

two

0.84

 deux

0.81

RetentionPolicy

0.78

 thrice

0.76

 BoxFit

0.76

0.75

Activations Density 1.318%

mathematical expressions and equations

No Comments

No Known Activations