INDEX

Explanations

phrases related to theories of liability and legal frameworks

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

 snippetHide

-0.60

antMatchers

-0.57

 kaarangay

-0.52

 Stab

-0.50

providedIn

-0.50

новниш

-0.50

 Acht

-0.50

ParallelGroup

-0.49

cesa

-0.49

 الاطلاع

-0.48

POSITIVE LOGITS

 theory

0.89

 THEORY

0.84

 Theory

0.79

theory

0.75

Theory

0.71

THEORY

0.69

 theories

0.63

 theorist

0.59

 teoria

0.58

 teori

0.58

Activations Density 0.000%

phrases related to theories of liability and legal frameworks

No Comments

No Known Activations