INDEX

Explanations

negations related to personal opinions or assessments

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

not sure or know

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

GOTREF

-0.78

tagHelperRunner

-0.72

 betweenstory

-0.70

+:+

-0.67

.*")]

-0.67

曖昧さ回避

-0.67

aarrggbb

-0.66

TagMode

-0.66

elemField

-0.66

 <=",

-0.64

POSITIVE LOGITS

 expertise

0.80

 firsthand

0.73

 expert

0.72

know

0.72

 knowledge

0.70

 specifics

0.70

 know

0.70

 knowledgeable

0.65

 knowled

0.65

Know

0.64

Activations Density 0.106%

negations related to personal opinions or assessments

not sure or know

No Comments

No Known Activations