INDEX

Explanations

phrases indicating analysis or study related concepts

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

 Kerr

-0.57

หวัด

-0.52

Kerr

-0.52

 Rangers

-0.52

 avail

-0.51

ursales

-0.51

[]:

-0.50

Abitanti

-0.50

cellaneous

-0.49

POSITIVE LOGITS

 تضيفلها

0.69

 odkazy

0.66

PyExc

0.66

 незавершена

0.63

abestanden

0.62

toHaveBeenCalled

0.62

BeginContext

0.62

ölkerung

0.62

 autorytatywna

0.61

脚注の使い方

0.60

Activations Density 0.095%

phrases indicating analysis or study related concepts

No Comments

No Known Activations