INDEX

Explanations

tokens that represent structured data or specific formatting elements, likely including brackets, commas, and numeric values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aarrggbb

-0.88

ArrowToggle

-0.85

oredCriteria

-0.74

Gambas

-0.71

addCriterion

-0.67

writeFieldEnd

-0.66

gatsby

-0.66

MigrationBuilder

-0.66

 propOrder

-0.63

 kasarigan

-0.62

POSITIVE LOGITS

出版年

0.63

bestos

0.58

IsContent

0.57

*/;

0.53

buah

0.50

EndContext

0.49

item

0.47

めました

0.46

InjectMocks

0.44

SourceChecksum

0.44

Activations Density 0.322%

tokens that represent structured data or specific formatting elements, likely including brackets, commas, and numeric values

No Comments

No Known Activations