INDEX

Explanations

nouns related to health and medical studies

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

MessageOf

-0.79

########.

-0.79

 оригіналу

-0.73

 Signalez

-0.71

BeginContext

-0.69

 InputDecoration

-0.68

 صوتيه

-0.68

principalTable

-0.68

ViewFeatures

-0.66

principalColumn

-0.66

POSITIVE LOGITS

 recent

0.48

enschein

0.48

ahan

0.48

ounced

0.48

 persist

0.47

aloo

0.45

IsSet

0.45

 presence

0.44

 persists

0.43

ngoing

0.43

Activations Density 0.045%

nouns related to health and medical studies

No Comments

No Known Activations