INDEX

Explanations

references to "box" or related concepts in various contexts

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

"box"

np_acts-logits-general · gemini-2.0-flash

box office and dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

béco

-0.63

########.

-0.61

UrlResolution

-0.59

DataAnnotations

-0.56

 jsPsych

-0.56

vements

-0.53

aporation

-0.52

RequestQueue

-0.52

 للمعارف

-0.52

roidery

-0.49

POSITIVE LOGITS

 office

0.76

office

0.75

OFFICE

0.71

 lunches

0.69

 OFFICE

0.68

lunch

0.67

Office

0.66

 Office

0.66

score

0.63

ercise

0.60

Activations Density 0.068%

references to "box" or related concepts in various contexts

"box"

box office and dimensions

No Comments

No Known Activations