INDEX

Explanations

numbers and symbols in the text

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

Numbers and symbols

np_acts-logits-general · gemini-2.0-flash

hexadecimal codes, dates, and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Rhestr

-0.76

Jereo

-0.52

spesies

-0.51

новниш

-0.51

HandlerContext

-0.49

govia

-0.48

 endblock

-0.47

 bắt

-0.47

 Bergh

-0.47

IsUnicode

-0.46

POSITIVE LOGITS

GIVEREF

0.69

észetes

0.59

TagMode

0.58

TypedDataSet

0.57

numerusform

0.56

wpi

0.56

ConstraintMaker

0.55

 inadmissible

0.55

Nearly

0.54

"]);

0.54

Activations Density 0.544%

numbers and symbols in the text

Numbers and symbols

hexadecimal codes, dates, and identifiers

No Comments

No Known Activations