INDEX

Explanations

symbols and mathematical expressions typically found in programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 acrylique

-0.54

 métallique

-0.52

 élé

-0.48

ieważ

-0.48

heritance

-0.47

cluso

-0.47

 végétale

-0.47

ocytosis

-0.46

held

-0.46

aard

-0.46

POSITIVE LOGITS

 propOrder

1.03

InjectAttribute

1.02

Personendaten

0.89

LookAnd

0.89

InstrumentedTest

0.88

 unknownFields

0.78

 noDo

0.78

 مشين

0.76

awtextra

0.75

 للاسماء

0.75

Activations Density 0.461%

symbols and mathematical expressions typically found in programming or technical contexts

No Comments

No Known Activations