INDEX

Explanations

references to file locations or downloadable documents

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

 disagre

-1.51

 apprehen

-1.46

 gaily

-1.43

 unspeak

-1.39

 snoopy

-1.37

 excru

-1.31

 unwarran

-1.31

 tolerably

-1.28

 jurassic

-1.28

 outlander

-1.26

POSITIVE LOGITS

twimg

0.63

SourceChecksum

0.59

img

0.57

cache

0.54

file

0.54

cdn

0.54

img

0.53

 ***!

0.53

 Ause

0.52

files

0.52

Activations Density 0.145%

references to file locations or downloadable documents

No Comments

No Known Activations