INDEX

Explanations

references to jaywalking and traffic-related behaviors

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

relating to "crossing"

np_acts-logits-general · gemini-2.0-flash

crossing roads and railroad tracks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 EconPapers

-0.66

تقاوى

-0.52

WireFormatLite

-0.52

aarrggbb

-0.52

MessageOf

-0.50

 ویکی‌پدی

-0.47

 चीज़ों

-0.47

 AssemblyTitle

-0.47

tangentMode

-0.46

tagHelperRunner

-0.45

POSITIVE LOGITS

 crossing

1.33

 Crossing

1.18

 crossings

1.13

crossing

1.12

 cross

1.07

Crossing

1.04

 crossed

1.03

 CROSS

0.94

 Cross

0.91

 crosses

0.91

Activations Density 0.112%

references to jaywalking and traffic-related behaviors

relating to "crossing"

crossing roads and railroad tracks

No Comments

No Known Activations