INDEX

Explanations

references to data structures and items in programming

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ONTO

-0.55

igneurs

-0.54

ProgressHUD

-0.53

 demurrer

-0.52

ⓧ

-0.52

beforeSend

-0.51

medad

-0.50

cism

-0.49

conda

-0.48

InputModule

-0.48

POSITIVE LOGITS

 للاسماء

0.67

Identyfik

0.66

SourceChecksum

0.63

 ProtoMessage

0.60

modelBuilder

0.59

parsedMessage

0.58

ThroughAttribute

0.57

…~

0.56

رشف

0.55

 GetEnumerator

0.55

Activations Density 0.159%

references to data structures and items in programming

No Comments

No Known Activations