INDEX

Explanations

phrases related to legal actions and warrants

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 soigne

-0.96

 trouva

-0.80

 broderie

-0.78

uhr

-0.76

 Chapitre

-0.75

 télécharge

-0.72

 Traité

-0.70

 triomphe

-0.69

 Violon

-0.68

 Kategor

-0.68

POSITIVE LOGITS

 issued

0.84

issued

0.68

 issuance

0.58

 notice

0.56

 notices

0.54

 instructing

0.53

 orders

0.52

 emanating

0.52

 issuing

0.51

 summoning

0.51

Activations Density 0.288%

phrases related to legal actions and warrants

No Comments

No Known Activations