INDEX

Explanations

positives related to technology and telecommunications devices

oai_token-act-pair · gemini-2.0-flash

expressions of gratitude

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

expressing thanks

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

HSSF

-0.45

sptr

-0.43

Xna

-0.40

spraak

-0.40

 umge

-0.40

 siyang

-0.40

例句

-0.40

tså

-0.39

 noDo

-0.38

gea

-0.38

POSITIVE LOGITS

 thanks

3.34

 Thanks

2.98

thanks

2.88

Thanks

2.84

 THANKS

2.61

 gracias

2.31

THANKS

2.14

 grazie

2.05

Gracias

2.02

thx

1.96

Activations Density 5.526%

positives related to technology and telecommunications devices

expressions of gratitude

expressing thanks

No Comments

No Known Activations