INDEX

Explanations

timestamp values in various formats

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

Citations to academic publications

np_acts-logits-general · gemini-2.0-flash

numbers and data citations

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

 unknownFields

-0.66

mergeFrom

-0.59

 Normdatei

-0.56

EREN

-0.56

 NSCoder

-0.56

그리고

-0.54

ۜ

-0.53

"]))

-0.53

 distanciation

-0.52

 kiến

-0.52

POSITIVE LOGITS

1.21

DataAnnotations

0.59

𝟬

0.56

０

0.55

thousand

0.53

 Thousand

0.52

۰۰

0.50

 thousand

0.49

𝟎

0.47

၀

0.45

Activations Density 0.183%

timestamp values in various formats

Citations to academic publications

numbers and data citations

No Comments

No Known Activations