INDEX

Explanations

terms related to telecommunications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

存于互联网档案馆

-0.97

antart

-0.81

interopRequire

-0.80

 تانيه

-0.78

 Hendrix

-0.75

ąż

-0.74

mirante

-0.73

AndEndTag

-0.73

__":

-0.72

ntag

-0.72

POSITIVE LOGITS

 tele

3.24

 Tele

3.18

Tele

2.83

tele

2.76

 TELE

2.57

TELE

2.29

 télé

2.01

 теле

1.68

 teleport

1.58

 Telecom

1.53

Activations Density 0.051%

terms related to telecommunications

No Comments

No Known Activations