INDEX

Explanations

terms related to physical structures or geographical features

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

aternion

-0.57

KommentareTeilen

-0.52

BagConstraints

-0.52

hoeddwyd

-0.52

Genuine

-0.50

 grund

-0.50

 '*':

-0.50

hikari

-0.49

 سل

-0.48

 xung

-0.48

POSITIVE LOGITS

WebVitals

0.62

addCriterion

0.59

 فريبيس

0.59

 Roskov

0.59

StreetMap

0.59

 Italijani

0.58

Smarty

0.58

 gynhyrchwyd

0.58

 насељу

0.58

 AssemblyTitle

0.57

Activations Density 0.096%

terms related to physical structures or geographical features

No Comments

No Known Activations