INDEX

Explanations

relevant sections or headlines within a document related to specific topics, possibly about laws, emissions, energy, or research institutes

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

 increa

-6.74

 reluct

-6.56

 inev

-6.38

 disagre

-6.31

 indestru

-6.31

 impra

-6.23

 affor

-6.18

 guarante

-6.16

 depic

-6.12

 maneu

-6.10

POSITIVE LOGITS

<bos>

11.28

 <>",

1.91

Autoritní

1.88

GEBURTSDATUM

1.86

1.85

 betweenstory

1.84

↵

1.81

 Paglinawan

1.80

1.79

 Italijani

1.78

Activations Density 0.060%

relevant sections or headlines within a document related to specific topics, possibly about laws, emissions, energy, or research institutes

No Comments

No Known Activations