INDEX

Explanations

technical discussions related to data science and system developments

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

ulity

-0.54

iastes

-0.52

又不是

-0.52

Бележки

-0.51

Tikang

-0.51

明明

-0.50

marginBottom

-0.50

cnia

-0.50

zional

-0.50

toplasm

-0.49

POSITIVE LOGITS

 challenges

1.54

challenges

1.39

 Challenges

1.31

 prospects

1.28

Challenges

1.25

 trends

1.24

 implications

1.19

 recent

1.19

 progress

1.14

 current

1.10

Activations Density 0.466%

technical discussions related to data science and system developments

No Comments

No Known Activations