INDEX

Explanations

places or locations and actions related to investigating or searching for evidence

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

 desir

-1.76

 guarante

-1.62

 perfet

-1.60

fuf

-1.60

 milf

-1.58

 embra

-1.58

 fath

-1.55

 gild

-1.54

 michelin

-1.52

 effe

-1.52

POSITIVE LOGITS

顺便

0.58

広場

0.57

 check

0.56

 дописавши

0.54

ypep

0.54

 <<<<<<<<<<<<<<

0.52

XMLSchema

0.52

进一步

0.52

 update

0.51

beiter

0.51

Activations Density 0.414%

places or locations and actions related to investigating or searching for evidence

No Comments

No Known Activations