INDEX

Explanations

mentions of speaking or understanding a language

oai_token-act-pair · gemini-2.0-flash

languages

np_max-act-logits · gemini-2.0-flash

speak

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 dům

-0.52

Diagnosis

-0.44

in

-0.44

 mortes

-0.44

 soutě

-0.43

SPECIFIED

-0.42

PhysRevD

-0.42

 tocado

-0.41

 bedste

-0.41

 scene

-0.41

POSITIVE LOGITS

SharedDtor

0.85

GOTREF

0.82

اریخ

0.75

StoryboardSegue

0.73

InputTagHelper

0.70

सन्दर्भ

0.68

 kasarigan

0.67

 سكانية

0.66

AnchorStyles

0.65

__(/*!

0.63

Activations Density 4.734%

mentions of speaking or understanding a language

languages

speak

No Comments

No Known Activations