INDEX

Explanations

words that often appear as part of a technical description in a scientific report

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Svet

-0.75

endous

-0.60

cinogen

-0.58

 '/')

-0.57

Jum

-0.57

gia

-0.57

%>

-0.56

 Administrativna

-0.55

quine

-0.54

("]");

-0.54

POSITIVE LOGITS

ιλ

0.69

Hochspringen

0.68

Datuak

0.66

 ExecuteAsync

0.66

__(/*!

0.65

ProcessEvent

0.65

 Forsyth

0.64

 ویکی‌پدیا

0.63

σιμοποι

0.60

 comprends

0.60

Activations Density 14.856%

words that often appear as part of a technical description in a scientific report

No Comments

No Known Activations