INDEX

Explanations

mathematical symbols and notations used in higher-level equations

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

aha

-0.46

вЂ

-0.46

cul

-0.44

mozilla

-0.44

مئ

-0.44

ismatic

-0.43

Two

-0.43

 Down

-0.42

Two

-0.42

Also

-0.42

POSITIVE LOGITS

 InputDecoration

0.98

 ExecuteAsync

0.90

elemField

0.85

出版年

0.82

 AssemblyTitle

0.79

HideFlags

0.77

 EconPapers

0.72

 BoxDecoration

0.71

UnknownFields

0.71

كويكب

0.68

Activations Density 0.204%

mathematical symbols and notations used in higher-level equations

No Comments

No Known Activations