INDEX

Explanations

indicators of documentation and references in texts

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

after periods

np_acts-logits-general · gemini-2.0-flash

briefly, essentially, basically

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

RectangleBorder

-0.86

 Dafür

-0.79

kháu

-0.75

ConstraintMaker

-0.74

 tartalomajánló

-0.74

 initComponents

-0.69

 Савезне

-0.68

 Biôgrafia

-0.68

Sucesor

-0.66

providedIn

-0.65

POSITIVE LOGITS

 Briefly

0.73

Essentially

0.66

Suff

0.63

 basically

0.62

 Essentially

0.58

Basically

0.58

 Basically

0.58

 essentially

0.57

 darin

0.56

basically

0.54

Activations Density 0.594%

indicators of documentation and references in texts

after periods

briefly, essentially, basically

No Comments

No Known Activations