INDEX

Explanations

complex mathematical expressions and equations

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

"W" followed by other characters

np_acts-logits-general · gemini-2.0-flash

W followed by letter

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

äher

-0.50

webElementXpaths

-0.46

-0.44

His

-0.41

ChildIndex

-0.41

His

-0.41

JsonInclude

-0.41

protoimpl

-0.40

 Exacts

-0.40

POSITIVE LOGITS

1.49

1.31

We

1.02

Ｗ

1.01

Ws

0.97

Wo

0.92

Wt

0.92

Ws

0.91

Wa

0.90

WS

0.86

Activations Density 0.609%

complex mathematical expressions and equations

"W" followed by other characters

W followed by letter

No Comments

No Known Activations