INDEX

Explanations

references to specific concepts or methodologies within educational or scientific contexts

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

terms related to medical information and research methodologies

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

abbreviations and technical terms

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

PerformLayout

-0.69

ostante

-0.68

lgari

-0.67

 mergeFrom

-0.66

 AppBundle

-0.65

DoubleQuotes

-0.64

 esterni

-0.63

 Bourgoin

-0.62

Zeneca

-0.62

giène

-0.62

POSITIVE LOGITS

same

0.66

0.65

 same

0.61

0.60

Same

0.59

0.58

PRET

0.57

blo

0.56

 Same

0.56

textbox

0.55

Activations Density 0.225%

references to specific concepts or methodologies within educational or scientific contexts

terms related to medical information and research methodologies

abbreviations and technical terms

No Comments

No Known Activations