INDEX

Explanations

language related to viruses and scientific research

oai_token-act-pair · gemini-2.0-flash

terms related to avian influenza

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

influenza, bird flu

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

transQ

-0.56

RenderAtEndOf

-0.50

ChildScrollView

-0.50

 Ανακτήθηκε

-0.48

Franklin

-0.46

Arco

-0.45

族館

-0.45

 Arce

-0.44

<?

-0.44

RectangleBorder

-0.44

POSITIVE LOGITS

influ

0.77

 Bird

0.77

Influ

0.76

 bird

0.72

 Influ

0.72

 avian

0.71

Bird

0.71

bird

0.66

 BIRD

0.66

0.65

Activations Density 2.038%

language related to viruses and scientific research

terms related to avian influenza

influenza, bird flu

No Comments

No Known Activations