INDEX

Explanations

terms related to medical and healthcare professions

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

awtextra

-0.81



-0.81

 EconPapers

-0.70

disposing

-0.69

참고

-0.69

thâu

-0.68

OGND

-0.67

zzar

-0.66

jspx

-0.65

ViewFeatures

-0.64

POSITIVE LOGITS

 krop

0.50

kob

0.47

 Obre

0.45

gensen

0.44

 accidente

0.43

 myself

0.43

getElementById

0.41

чер

0.41

LLO

0.41

יתי

0.40

Activations Density 0.080%

terms related to medical and healthcare professions

No Comments

No Known Activations