INDEX

Explanations

terms related to medical and clinical terminology

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

supra shoes

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

 MessageBoxIcon

-0.40

+:+

-0.39

 XCTest

-0.36

 ModelExpression

-0.35

agrid

-0.35

 Normdatei

-0.35

 AssemblyVersion

-0.34

prepar

-0.34

aff

-0.34

 Received

-0.33

POSITIVE LOGITS

StoryboardSegue

0.67

 Administrativna

0.65

 disambiguazione

0.54

 otomatig

0.52

 Infór

0.49

expandindo

0.49

 transparencia

0.47

 للمعارف

0.46

protoimpl

0.45

 desmotivaciones

0.44

Activations Density 0.012%

terms related to medical and clinical terminology

supra shoes

No Comments

No Known Activations