INDEX

Explanations

references to body parts and their interactions in a medical context

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

body divisions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Lingkungan

-0.40

 Wiktionnaire

-0.40

 sèche

-0.39

 bolsillo

-0.37

 protoimpl

-0.37

 garansi

-0.37

 fumée

-0.36

 CreateTagHelper

-0.36

 stanga

-0.35

IsContent

-0.34

POSITIVE LOGITS

 torso

0.57

半身

0.50

 Body

0.50

 snak

0.48

 BODY

0.47

 pant

0.47

 TextAlign

0.47

 getItem

0.46

 body

0.46

Activations Density 0.166%

references to body parts and their interactions in a medical context

body divisions

No Comments

No Known Activations