INDEX

Explanations

phrases related to legal documents and government actions

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

 hairc

-1.02

 intersper

-0.80

 hentai

-0.78

 indescri

-0.77

 milf

-0.77

 funko

-0.76

 embodi

-0.76

 amigurumi

-0.73

 depic

-0.73

 emphat

-0.73

POSITIVE LOGITS

 January

0.54

effective

0.51

Vidite

0.49

January

0.49

 February

0.48

 effective

0.48

 accogli

0.48

Effective

0.48

 kela

0.47

生效

0.47

Activations Density 0.241%

phrases related to legal documents and government actions

No Comments

No Known Activations