INDEX

Explanations

programming-related terms and actions associated with user interface and module management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

OGND

-0.99

ThroughAttribute

-0.76

ScopeManager

-0.69

Hochspringen

-0.61

WithIOException

-0.60

 wireType

-0.54

 jScrollPane

-0.53

 CommandType

-0.52

 насељу

-0.51

MarshalTo

-0.50

POSITIVE LOGITS

 فريبيس

0.66

ENOMEM

0.59

 stället

0.56

Попис

0.56

StoryboardSegue

0.56

väg

0.54

ymce

0.54

 Messieurs

0.53

 varandra

0.52

 Misses

0.52

Activations Density 0.057%

programming-related terms and actions associated with user interface and module management

No Comments

No Known Activations