INDEX

Explanations

terms related to disabilities and health conditions

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

physical or mental conditions and impairments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

AnchorTagHelper

-0.68

findpost

-0.65

ChildScrollView

-0.60

 BoxFit

-0.57

تقاوى

-0.57

 становника

-0.54

期刊论文

-0.54

"])

-0.54

出版年

-0.53

 Spot

-0.52

POSITIVE LOGITS

 disabilities

0.38

 trastornos

0.34

 Infór

0.33

 ujednoznacz

0.33

 ſever

0.32

 disorders

0.31

 fís

0.31

 miliki

0.31

 diseases

0.31

 physical

0.31

Activations Density 0.053%

terms related to disabilities and health conditions

physical or mental conditions and impairments

No Comments

No Known Activations