INDEX

Explanations

occurrences of placeholder characters or symbols often used in code or data structures

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

rrggbb

-0.54

 naturen

-0.52

 secas

-0.51

 verticale

-0.47

 mirar

-0.46

 verste

-0.46

 supérieures

-0.46

 sufficiente

-0.46

 remercier

-0.46

 favorito

-0.45

POSITIVE LOGITS

 كومونز

0.80

 ***!

0.72

XmlRootElement

0.68

GraphicsUnit

0.67

sizeCache

0.66

 لينك

0.66

fjspx

0.66

__(/*!

0.65

 autorytatywna

0.64

0.63

Activations Density 0.121%

occurrences of placeholder characters or symbols often used in code or data structures

No Comments

No Known Activations