INDEX

Explanations

technical terms related to classification or categorization processes

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

technical terms related to air purification processes

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

codifies, codified, refaction

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

ates

-0.94

ate

-0.91

ATE

-0.90

ATES

-0.86

rate

-0.76

rates

-0.69

ately

-0.67

 rates

-0.67

nate

-0.67

 rate

-0.67

POSITIVE LOGITS

WithIOException

0.68

ConstraintMaker

0.63

(!__

0.63

 obé

0.60

 الدولى

0.59

 himo

0.58

 civiles

0.57

viewDidLoad

0.56

pitaux

0.55

المكان

0.55

Activations Density 0.131%

technical terms related to classification or categorization processes

technical terms related to air purification processes

codifies, codified, refaction

No Comments

No Known Activations