INDEX

Explanations

mathematical expressions and formal notations related to sequences and functions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

LaTeX "text" and related commands

np_acts-logits-general · gemini-2.0-flash

text and textnormal

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

Negative Logits

 initComponents

-0.70

CPtr

-0.60

 igre

-0.54

//

-0.54

nestjs

-0.53

sizeCache

-0.52

 TestBed

-0.49

 ✭✭

-0.48

মা

-0.48

ंदीखरीदारी

-0.48

POSITIVE LOGITS

text

1.15

 text

0.95

 Text

0.82

 TEXT

0.73

 texts

0.71

 texte

0.70

Text

0.67

 getText

0.66

 texto

0.65

 Texts

0.64

Activations Density 0.312%

mathematical expressions and formal notations related to sequences and functions

LaTeX "text" and related commands

text and textnormal

No Known Activations