INDEX

Explanations

numerical values and figures mentioned in the text

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

Dollar amounts

np_acts-logits-general · gemini-2.0-flash

numbers separated by commas

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

 kasarigan

-0.76

Билгалдахарш

-0.68

NameInMap

-0.58

Einzelnachweise

-0.55

 esternos

-0.55

'])){

-0.54

blet

-0.53

ⓧ

-0.52

发布于

-0.52

ThroughAttribute

-0.50

POSITIVE LOGITS

0.78

0.66

0.62

0.57

0.55

nachron

0.52

 itſelf

0.51

xx

0.51

Activations Density 0.263%

numerical values and figures mentioned in the text

Dollar amounts

numbers separated by commas

No Comments

No Known Activations