INDEX

Explanations

references to toxicological standards and guidelines related to exposure limits

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

reference values and limits

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

ContentAsync

-0.49

 sandpaper

-0.44

UpInside

-0.44

errHandler

-0.42

EndInit

-0.42

 dope

-0.41

 مشين

-0.40

:^(

-0.39

:✨

-0.39

 twine

-0.39

POSITIVE LOGITS

 critères

0.57

 criteria

0.56

 limits

0.54

 standards

0.49

 Criteria

0.48

 ujednoznacz

0.47

 limit

0.47

 normes

0.47

limits

0.46

 tolerances

0.46

Activations Density 0.021%

references to toxicological standards and guidelines related to exposure limits

reference values and limits

No Comments

No Known Activations