INDEX

Explanations

mathematical symbols and notations related to matrices and estimators

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

pekte

-0.51

(&:

-0.47

ukunft

-0.47

Citiți

-0.47

zerne

-0.46

roughts

-0.46

 riuscito

-0.45

 picioare

-0.45

adori

-0.45

 înal

-0.45

POSITIVE LOGITS

IndentedString

0.77

ValueStyle

0.62

 utafitiHapana

0.60

ządu

0.60

brigens

0.57

 חיצוניים

0.57

 Wicidata

0.56

matchCondition

0.55

abestanden

0.55

elemField

0.55

Activations Density 0.668%

mathematical symbols and notations related to matrices and estimators

No Comments

No Known Activations