INDEX

Explanations

words related to lightbulbs

oai_token-act-pair · gemini-2.0-flash

programming-related terms or jargon

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

Computer code and lights

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AllAfrica

-0.52

MessageOf

-0.51

zło

-0.50

+#+

-0.47

 dones

-0.47

ersdorf

-0.47

)\}$

-0.47

텝

-0.46

led

-0.46

StackSize

-0.46

POSITIVE LOGITS

cshtml

0.62

SizeF

0.60

 itchy

0.56

DrawerToggle

0.51

::*;

0.51

urezza

0.51

Referencies

0.51

 pinulongan

0.50

ńcu

0.50

cy

0.50

Activations Density 0.714%

words related to lightbulbs

programming-related terms or jargon

Computer code and lights

No Comments

No Known Activations