INDEX

Explanations

mathematical formulas

oai_token-act-pair · gemini-2.0-flash

mathematical notation in physics papers

np_token-act-pair-logits · gemini-2.0-flash

math/physics equations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

LEncoder

-1.14

 ―――――

-0.96

 myſelf

-0.94

rungsseite

-0.92

+:+

-0.91

帖最后由

-0.89

ScopeManager

-0.88

TypedDataSet

-0.87

DockStyle

-0.87

UrlResolution

-0.86

POSITIVE LOGITS

↵↵

0.83

<eos>

0.68

↵↵↵

0.49

0.44

0.42

Let

0.40

un

0.39

let

0.39

↵↵↵↵

0.38

 Peter

0.38

Activations Density 3.812%

mathematical formulas

mathematical notation in physics papers

math/physics equations

No Comments

No Known Activations