INDEX

Explanations

written information or text related to various documents or publications

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

-0.89

 swarovski

-0.83

 Shakspeare

-0.76

 cushi

-0.75

 snapback

-0.74

 Membre

-0.74

»>

-0.73

 murano

-0.72

 matel

-0.71

 tupperware

-0.71

POSITIVE LOGITS

 printed

0.71

 paper

0.64

 printing

0.64

printed

0.58

 booklet

0.55

Printed

0.54

 print

0.54

 printer

0.54

 printers

0.51

 sheets

0.51

Activations Density 0.707%

written information or text related to various documents or publications

No Comments

No Known Activations