INDEX

Explanations

technical terms and jargon related to online services and verification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 sena

-0.51

Și

-0.49

posób

-0.48

rawy

-0.46

 représentation

-0.46

wiec

-0.45

uels

-0.45

HALT

-0.44

 stocking

-0.44

pasto

-0.44

POSITIVE LOGITS

 للمعارف

0.95

出版年

0.88

 Chwiliwch

0.84

 utafitiHapana

0.79

transQ

0.79

 MainAxisSize

0.78

 ModelExpression

0.77

 ddelweddau

0.75

+#+#

0.75

InSection

0.71

Activations Density 0.056%

technical terms and jargon related to online services and verification processes

No Comments

No Known Activations