INDEX

Explanations

words relevant to group discussion, communication, and organizations

oai_token-act-pair · gemini-2.0-flash

communication

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 houſe

-0.91

 Houſe

-0.87

ConstraintMaker

-0.86

Efq

-0.85

 againſt

-0.85

eabouts

-0.78

 ſtill

-0.77

extAlignment

-0.77

Eſ

-0.73

 Reſ

-0.73

POSITIVE LOGITS

 caratteristiche

0.43

 particulières

0.41

rak

0.40

 esfuerzo

0.40

 muros

0.39

mba

0.38

pi

0.38

 muro

0.38

 giải

0.38

 gynhyrchwyd

0.37

Activations Density 5.864%

words relevant to group discussion, communication, and organizations

communication

No Comments

No Known Activations