INDEX

Explanations

mathematical structures or formatting related to arrays

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

చ్

-0.49

規

-0.43

msgSender

-0.41

Hi

-0.41

-0.40

roles

-0.38

te

-0.37

Mar

-0.36

 düş

-0.36

 חי

-0.35

POSITIVE LOGITS

 فريبيس

0.87

 ModelExpression

0.83

 ―――――

0.81

principalColumn

0.79

FunctionFlags

0.74

 Vikipedi

0.73

ksikon

0.73

Spoljašnje

0.72

SBATCH

0.72

➟

0.70

Activations Density 0.087%

mathematical structures or formatting related to arrays

No Comments

No Known Activations