INDEX

Explanations

financial information, especially losses

oai_token-act-pair · gemini-2.0-flash

uncommon or nonsensical tokens

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

Large numbers and geopolitical events

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

AddHtmlAttribute

-0.65

GOTREF

-0.63

basicConfig

-0.57

ImageContext

-0.57

مصادر

-0.56

Попис

-0.55

الحياه

-0.54

BNE

-0.54

 SwitchCompat

-0.53

ariado

-0.52

POSITIVE LOGITS

 Tiên

0.47

tschafts

0.46

 quebra

0.46

一目

0.46

="@+

0.43

 tør

0.42

Bakgrunnsstoff

0.41

BREAK

0.41

Predecesor

0.41

Skocz

0.40

Activations Density 1.069%

financial information, especially losses

uncommon or nonsensical tokens

Large numbers and geopolitical events

No Comments

No Known Activations