INDEX

Explanations

terms related to selection and determination processes

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

findpost

-0.85

abestanden

-0.82

featureID

-0.77

 propOrder

-0.71

 initComponents

-0.71

 Wayback

-0.68

GEBURTSDATUM

-0.68

 للمعارف

-0.67

 invokingState

-0.66

 gyhoeddwyd

-0.65

POSITIVE LOGITS

 Bench

0.51

sé

0.46

BASEPATH

0.46

 learned

0.45

Bench

0.45

utare

0.44

shadowOpacity

0.42

рена

0.42

サーチ

0.42

 based

0.42

Activations Density 0.159%

terms related to selection and determination processes

No Comments

No Known Activations

terms related to selection and determination processes

No Comments

No Known Activations