INDEX

Explanations

references to medical cases, patients, and studies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

reports of medical cases

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nombreux

-0.63

 רבים

-0.62

 numerosas

-0.60

 centaines

-0.59

 wielu

-0.59

 birçok

-0.59

 lenker

-0.59

 berbagai

-0.59

 Wiktionnaire

-0.58

 nombreuses

-0.57

POSITIVE LOGITS

 apiece

0.91

分别是

0.85

 namely

0.80

分別

0.75

 each

0.71

 respectively

0.70

namely

0.68

each

0.65

 consecutively

0.64

 consecu

0.63

Activations Density 0.241%

references to medical cases, patients, and studies

reports of medical cases

No Comments

No Known Activations