INDEX

Explanations

references to lists, particularly in the context of organization or classification

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

 <<<<<<<<<<<<<<

-0.80

 OGSÅ

-0.70

 resourceCulture

-0.65

TextAppearance

-0.60

CodeAnalysis

-0.59

 الأصل

-0.57

 noDo

-0.57

cue

-0.56

tilia

-0.55

URLException

-0.54

POSITIVE LOGITS

 peindre

0.50

 zijne

0.48

rungsseite

0.47

 daarom

0.47

 sólidos

0.46

HEAST

0.46

 vermeld

0.46

 berapa

0.45

 portátiles

0.45

mlı

0.45

Activations Density 0.002%

references to lists, particularly in the context of organization or classification

No Comments

No Known Activations