INDEX

Explanations

elements related to scientific notation and computational structures

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

Text inside brackets or parentheses

np_acts-logits-general · gemini-2.0-flash

punctuation followed by letters

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

 Bourgoin

-0.56

jois

-0.48

msgTypes

-0.47

 elkaar

-0.46

 gawas

-0.46

 heights

-0.46

quia

-0.46

<h6>

-0.46

Lut

-0.46

','.

-0.45

POSITIVE LOGITS

جغرافيا

0.67

WithIOException

0.65

getDoctrine

0.63

 endblock

0.61

 estimés

0.59

ioutil

0.56

 Bioaccumulative

0.56

ypress

0.54

essoal

0.53

 ModelExpression

0.52

Activations Density 0.879%

elements related to scientific notation and computational structures

Text inside brackets or parentheses

punctuation followed by letters

No Comments

No Known Activations