INDEX

Explanations

terms related to ergonomics and ergonomic design

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

ergonomic

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

 '\\;'

-0.45

IsContent

-0.44

 saites

-0.41

GEBURTSDATUM

-0.40

 preghi

-0.40

 utafitiHapana

-0.40

 verhalen

-0.39

 fotografico

-0.39

 onPostExecute

-0.39

 BorderSide

-0.38

POSITIVE LOGITS

 ergonomic

1.05

 ergonomics

1.03

 ergonom

1.00

 Ergonomic

0.89

Erg

0.81

Erg

0.73

 ergon

0.70

 ergo

0.56

erg

0.55

 comfort

0.53

Activations Density 0.006%

terms related to ergonomics and ergonomic design

ergonomic

No Comments

No Known Activations