INDEX

Explanations

terms related to imaging technology and procedures

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

CT imaging types

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

Negative Logits

 незавершена

-0.65

WithIOException

-0.63

CloseOperation

-0.61

 desmotivaciones

-0.61

цездатний

-0.57

errHandler

-0.55

serviceWorker

-0.54

elezo

-0.50

省市镇

-0.50

argout

-0.50

POSITIVE LOGITS

 wild

0.36

rid

0.36

dis

0.33

 stepped

0.33

ULO

0.33

Dis

0.32

den

0.31

car

0.31

 knock

0.31

 Wild

0.30

Activations Density 0.492%

terms related to imaging technology and procedures

CT imaging types

No Known Activations