INDEX

Explanations

mathematical symbols and equations, especially those within scientific papers

oai_token-act-pair · gemini-2.0-flash

specialized terminology or jargon

np_token-act-pair-logits · gpt-4o-mini

Physics equations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:][

-0.57

 تانيه

-0.56

[]:

-0.50

 springfox

-0.49

istar

-0.49

uria

-0.44

ób

-0.44

 sich

-0.44

chkin

-0.44

urian

-0.43

POSITIVE LOGITS

Демографія

0.84

PreferredItem

0.79

Handlung

0.67

 صوتيه

0.67

δρ

0.60

GNP

0.58

 EconPapers

0.57

SPS

0.56

ContentAsync

0.56

Datuak

0.56

Activations Density 4.465%

mathematical symbols and equations, especially those within scientific papers

specialized terminology or jargon

Physics equations

No Comments

No Known Activations