INDEX

Explanations

terminology related to warranties and legal disclaimers in product descriptions

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

-0.56

-0.52

 stock

-0.51

:✨

-0.50

 your

-0.48

</strong>

-0.47

or

-0.47

cu

-0.47

POSITIVE LOGITS

DockStyle

0.84

 MERCHANTABILITY

0.80

riwal

0.79

 ―――――

0.77

]='\

0.77

 auffi

0.73

saraba

0.71

extAlignment

0.71

 referenties

0.71

 BorderSide

0.70

Activations Density 0.005%

terminology related to warranties and legal disclaimers in product descriptions

No Comments

No Known Activations