INDEX

Explanations

terms related to necrosis and tissue death

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

Negative Logits

 démocr

-0.83

 Budd

-0.72

 alimentaire

-0.71

 chuva

-0.67

quién

-0.67

 Buda

-0.66

 telefónica

-0.66

readLine

-0.66

CVT

-0.66

 contemporain

-0.65

POSITIVE LOGITS

 necrosis

1.52

 Necro

1.27

 necro

1.26

Nec

1.07

Nec

1.04

nec

0.92

nec

0.74

tanleria

0.71

NEC

0.66

nek

0.63

Activations Density 0.001%

terms related to necrosis and tissue death

No Known Activations