INDEX

Explanations

names of individuals

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

 affez

-0.90

 appunt

-0.83

 attravers

-0.80

 peggio

-0.80

 attesa

-0.80

 ristor

-0.79

 soggior

-0.79

pæ

-0.79

 pranzo

-0.78

 letti

-0.77

POSITIVE LOGITS

 Poincar

0.72

 Levant

0.71

 Photographie

0.69

 Hopf

0.66

 Borel

0.63

 Ressource

0.63

 Strukt

0.62

 Lettre

0.62

 Poin

0.61

 IUPAC

0.60

Activations Density 0.118%

names of individuals

No Comments

No Known Activations