INDEX

Explanations

language related to government and politics

oai_token-act-pair · gemini-2.0-flash

words related to inquiries or questions

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

Parliament

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

MigrationBuilder

-1.10

RectangleBorder

-1.10

GOTREF

-0.93

 myſelf

-0.93

ImageContext

-0.91

 مشين

-0.85

 utafitiHapana

-0.81

цездатний

-0.79

MLLoader

-0.79

AddTagHelper

-0.79

POSITIVE LOGITS

 Question

0.56

 soru

0.53

Question

0.52

 question

0.50

Car

0.45

 questions

0.44

ؤال

0.43

Har

0.42

Ou

0.42

 star

0.42

Activations Density 0.562%

language related to government and politics

words related to inquiries or questions

Parliament

No Comments

No Known Activations