INDEX

Explanations

terminology related to medical conditions and their associated events or symptoms

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

adverse effects and symptoms

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

 pageable

-0.47

 ligiloj

-0.44

ServletConfig

-0.40

richlet

-0.39

Tikang

-0.39

romycin

-0.38

AntiForgeryToken

-0.38

 informée

-0.37

mothers

-0.37

@"/

-0.36

POSITIVE LOGITS

 symptoms

0.64

symptoms

0.55

Symptoms

0.52

httphttps

0.49

STOT

0.48

 manifestations

0.48

 effects

0.47

 Symptoms

0.46

effects

0.43

 symptom

0.43

Activations Density 0.000%

terminology related to medical conditions and their associated events or symptoms

adverse effects and symptoms

No Comments

No Known Activations