INDEX

Explanations

phrases relevant to legal proceedings and judicial terminology

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

Unmarshaller

-0.66

MessageOf

-0.65

afficheront

-0.63

GEBURTS

-0.60

 ModelRenderer

-0.60

geführten

-0.59

 FetchType

-0.57

 disambiguazione

-0.57

 Grom

-0.56

ParseTree

-0.54

POSITIVE LOGITS

enumi

0.79

 فريبيس

0.67

 שוליים

0.58

 rowspan

0.56

 CreateTagHelper

0.52

 sánh

0.51

ileo

0.49

paraiso

0.49

biet

0.48

ξω

0.48

Activations Density 0.108%

phrases relevant to legal proceedings and judicial terminology

No Comments

No Known Activations

phrases relevant to legal proceedings and judicial terminology

No Comments

No Known Activations