INDEX

Explanations

scientific articles and references, with a focus on content related to neurology

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

licet

-0.42

RTCF

-0.39

 saja

-0.39

as

-0.38

 rank

-0.38

atable

-0.38

ума

-0.38

 चीज़ों

-0.38

 crash

-0.37

"#

-0.37

POSITIVE LOGITS

PhysRevD

0.85

ConstraintMaker

0.84

PhysRevLett

0.78

 confirming

0.68

Cyfeiriadau

0.68

SuspendLayout

0.68

Демографія

0.67

 незавершена

0.66

PasswordEncoder

0.64

featureID

0.64

Activations Density 0.118%

scientific articles and references, with a focus on content related to neurology

No Comments

No Known Activations