INDEX

Explanations

symbols and names associated with regulations and policies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.20

osoba

-0.70

뉘

-0.63

 butterknife

-0.63

 Roskov

-0.60

GEBURTSDATUM

-0.59

ⓧ

-0.59

Њ

-0.58

 Meksiku

-0.58

ofern

-0.58

POSITIVE LOGITS

 unwarran

1.43

 increa

1.36

 impra

1.31

 lele

1.29

 jaya

1.28

 affor

1.28

 stockholm

1.27

Juf

1.26

 impractica

1.24

 strick

1.22

Activations Density 0.200%

symbols and names associated with regulations and policies

No Comments

No Known Activations