INDEX

Explanations

mathematical symbols and expressions related to functions and equations

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

Mathematical or statistical notation

np_acts-logits-general · gemini-2.0-flash

$a_{1},a_{2}$

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

SpringBootTest

-0.82

 calendriers

-0.76

 <>",

-0.73

dafx

-0.73

oa̍t

-0.71

"]),

-0.71

 Signalez

-0.71

IBOutlet

-0.69

 Fleur

-0.68

Попис

-0.67

POSITIVE LOGITS

躇

0.58

text

0.47

uj

0.46

кспер

0.44

Autoritní

0.44

dė

0.43

слав

0.42

why

0.42

 obro

0.42

Activations Density 1.011%

mathematical symbols and expressions related to functions and equations

Mathematical or statistical notation

$a_{1},a_{2}$

No Comments

No Known Activations