INDEX

Explanations

nouns related to politics, government, and organizations

oai_token-act-pair · gemini-2.0-flash

references to political claims and accusations

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

Formal contexts/statements

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

Negative Logits

GIVEREF

-0.48

getManager

-0.47

 senz

-0.46

onel

-0.46

 przód

-0.45

Рек

-0.44

 silnika

-0.42

 capilar

-0.42

 Sien

-0.42

its

-0.41

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.87

 الحره

0.82

 архивлан

0.81

RenderAtEndOf

0.78

enumii

0.74

 autorytatywna

0.73

новништво

0.73

 AssemblyVersion

0.68

ConstraintMaker

0.67

WriteBarrier

0.66

Activations Density 6.718%

nouns related to politics, government, and organizations

references to political claims and accusations

Formal contexts/statements

No Known Activations