INDEX

Explanations

phrases related to racing events and obstacles encountered during races

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

punctuation and special characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 projects

-0.67

 Projects

-0.64

 Grecs

-0.62

 affitto

-0.61

 måned

-0.61

íaca

-0.60

 progettazione

-0.60

 prêtres

-0.59

funda

-0.59

projects

-0.59

POSITIVE LOGITS

 early

0.69

 <<<<<<<<<<<<<<

0.66

0.64

early

0.60

 leaderboard

0.59

 briefly

0.58

IContainer

0.57

Geplaatst

0.55

 sempat

0.54

CodeAttribute

0.52

Activations Density 0.016%

phrases related to racing events and obstacles encountered during races

punctuation and special characters

No Comments

No Known Activations