INDEX

Explanations

terms related to safety equipment and protective gear

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

essential to protection/safety

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 MainAxisSize

-0.59

ьаж

-0.59

SourceChecksum

-0.57

oneofs

-0.56

 Biôgrafia

-0.54

atisfied

-0.51

delwed

-0.51

exitRule

-0.51

 onData

-0.51

 AssemblyCulture

-0.50

POSITIVE LOGITS

 wear

0.41

 wearing

0.41

 protectora

0.40

 protec

0.37

 protective

0.37

 Wear

0.35

Precautionary

0.34

 wore

0.33

 Wearing

0.33

 precaution

0.32

Activations Density 0.001%

terms related to safety equipment and protective gear

essential to protection/safety

No Comments

No Known Activations