INDEX

Explanations

technical terms and concepts related to JavaScript object properties and their configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Efq

-1.38

 Monfieur

-1.29

 Majefty

-1.23

 myſelf

-1.17

 Houſe

-1.15

 houſe

-1.10

tvguidetime

-1.10

Eſ

-1.10

 pleaſure

-1.07

 raiſ

-1.06

POSITIVE LOGITS

0.49

0.42

 mais

0.42

 question

0.40

 press

0.38

man

0.36

0.35

“

0.35

 process

0.34

sua

0.34

Activations Density 0.054%

technical terms and concepts related to JavaScript object properties and their configurations

No Comments

No Known Activations