INDEX

Explanations

references to Amazon and its products or services

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omla

-0.75

FunctionFlags

-0.75

blende

-0.70

antaranya

-0.66

RenderAtEndOf

-0.63

Caleb

-0.60

 Caleb

-0.59

wyk

-0.59

encre

-0.59

λλά

-0.59

POSITIVE LOGITS

 Amazon

1.78

Amazon

1.66

amazon

1.56

 amazon

1.55

 AMAZON

1.41

 Amaz

1.20

mazon

1.17

 Amazonas

1.13

Zon

1.08

Amaz

1.07

Activations Density 0.008%

references to Amazon and its products or services

No Comments

No Known Activations