INDEX

Explanations

terms related to subcategories or subpopulations in scientific contexts

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

 Waray

-0.74

клопе

-0.73

 Brasileira

-0.68

isien

-0.67

❹

-0.67

visiae

-0.66

 scolaires

-0.65

SKS

-0.64

mpl

-0.64

envolvimento

-0.63

POSITIVE LOGITS

Demografía

0.75

jois

0.68

AxisAlignment

0.66

modb

0.66

ollectionView

0.66

Zep

0.64

awtextra

0.63

 estimés

0.60

!*\

0.60

sub

0.59

Activations Density 0.015%

terms related to subcategories or subpopulations in scientific contexts

No Comments

No Known Activations

terms related to subcategories or subpopulations in scientific contexts

No Comments

No Known Activations