INDEX

Explanations

phrases related to lists in various formats

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

"List" or "list"

np_acts-logits-general · gemini-2.0-flash

List the prime factors

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

imageshack

-0.70

>>>>>>>>

-0.68

flasche

-0.66

طلحات

-0.63

CloseOperation

-0.60

hogy

-0.60

+#+

-0.60

 courthouse

-0.59

AJAS

-0.59

 GenerationType

-0.59

POSITIVE LOGITS

 list

1.28

 LIST

1.28

 Lists

1.26

 lists

1.23

 mList

1.20

 List

1.18

list

1.16

LIST

1.11

 itemList

1.11

 newList

1.08

Activations Density 0.102%

phrases related to lists in various formats

"List" or "list"

List the prime factors

No Comments

No Known Activations