INDEX

Explanations

phrases related to incidents, such as accidents, crimes, and police activities

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

-1.47

 swarovski

-1.45

 ecru

-1.41

 cushi

-1.34

 embodi

-1.34

 bordeaux

-1.30

 madonna

-1.30

 tupperware

-1.28

 impra

-1.27

 eiffel

-1.26

POSITIVE LOGITS

<bos>

1.01

InitVars

0.71

 investigation

0.68

 suspect

0.61

 investigations

0.61

Референце

0.59

 preliminary

0.59

 investigating

0.56

investigation

0.56

 preliminar

0.56

Activations Density 0.283%

phrases related to incidents, such as accidents, crimes, and police activities

No Comments

No Known Activations