INDEX

Explanations

phrases related to thievery and counteractions in response to theft

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

hcm

-0.90

aen

-0.84

 shutterstock

-0.84

 pixabay

-0.81

mef

-0.80

 rafra

-0.80

fto

-0.78

 Augu

-0.78

 squa

-0.78

 proprement

-0.76

POSITIVE LOGITS

InkWell

0.60

ánto

0.57

 deleteAll

0.56

relenting

0.56

ⓧ

0.53

xFFFFFFFF

0.50

tagHelper

0.50

 onStop

0.50

 viewWillAppear

0.49

 thrive

0.49

Activations Density 0.380%

phrases related to thievery and counteractions in response to theft

No Comments

No Known Activations