INDEX

Explanations

technical terms and references related to technology and digital platforms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

stateProvider

-0.54

šanās

-0.47

 umgekehrt

-0.44

代わりに

-0.40

besondere

-0.40

逆に

-0.40

-0.39

Especially

-0.38

-0.37

POSITIVE LOGITS

 designed

1.49

 featuring

1.35

 consisting

1.25

 capable

1.23

 aimed

1.21

designed

1.17

 requiring

1.16

 containing

1.16

 comprised

1.15

featuring

1.13

Activations Density 0.625%

technical terms and references related to technology and digital platforms

No Comments

No Known Activations