INDEX

Explanations

mentions related to legislative actions, bills, and government activities, particularly focusing on a specific bill or legislation introduced in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ecru

-1.51

 swarovski

-1.41

 hairc

-1.30

 cushi

-1.27

 indestru

-1.26

 broderie

-1.26

 snoopy

-1.16

 bordeaux

-1.16

 disreg

-1.15

 yoda

-1.14

POSITIVE LOGITS

 bill

0.69

 legislation

0.66

 tramit

0.62

 proposed

0.61

 praktik

0.58

 elektronik

0.58

 legislative

0.58

 proposal

0.58

 kosme

0.58

 draft

0.57

Activations Density 0.497%

mentions related to legislative actions, bills, and government activities, particularly focusing on a specific bill or legislation introduced in various contexts

No Comments

No Known Activations