INDEX

Explanations

technical terms and specifications related to programmable devices and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ועל

-0.46

san

-0.45

IMPORTED

-0.45

নে

-0.44

 Kirk

-0.43

urnya

-0.42

Unione

-0.42

hta

-0.42

 发表于

-0.41

mede

-0.41

POSITIVE LOGITS

 ddelweddau

0.96

 للمعارف

0.90

Rhestr

0.84

AsUp

0.82

 utafitiHapana

0.80

IsContent

0.80

AndEndTag

0.79

 initComponents

0.78

 DBNull

0.78

المناصب

0.77

Activations Density 0.649%

technical terms and specifications related to programmable devices and their components

No Comments

No Known Activations