INDEX

Explanations

phrases indicating legal actions and consequences

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

 муніципалі

-0.54

derna

-0.51

клопе

-0.50

šanai

-0.48

Active

-0.48

 peores

-0.46

 empe

-0.45

 active

-0.45

active

-0.45

دانشنامهٔ

-0.44

POSITIVE LOGITS

 JpaRepository

0.68

 MonoBehaviour

0.66

TemporalType

0.66

ScopeManager

0.63

 الحره

0.60

ConstraintMaker

0.59

OGND

0.59

 sockaddr

0.57

selves

0.57

Conteúdo

0.56

Activations Density 0.391%

phrases indicating legal actions and consequences

No Comments

No Known Activations