INDEX

Explanations

words from French and technical terms related to Linux.

oai_token-act-pair · gemini-2.0-flash

French snippets/software

np_max-act · gemini-2.0-flash

plus Method used: 1 — because the max-activating tokens are repeated forms of "plus"

np_max-act-logits · gpt-5-mini Triggered by @chenshw0109

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<bos>

-0.81

Short

-0.65

 Short

-0.59

 архивлан

-0.57

the

-0.56

<strong>

-0.50

short

-0.48

 particular

-0.48

 Privacidade

-0.48

It

-0.47

POSITIVE LOGITS

DockStyle

0.68

 numberOfRows

0.62

 Réponses

0.62

 Thermostat

0.62

PMI

0.61

esModule

0.60

Referències

0.60

 doute

0.60

quiel

0.60

VersionUID

0.59

Activations Density 0.274%

words from French and technical terms related to Linux.

French snippets/software

plus Method used: 1 — because the max-activating tokens are repeated forms of "plus"

No Comments

No Known Activations