INDEX

Explanations

technical terms and concepts related to machine learning and statistical estimators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-0.51

setUse

-0.45

Mas

-0.43

mas

-0.42

Mr

-0.42

Tr

-0.42

 previously

-0.41

é

-0.41

Dr

-0.40

 Tony

-0.40

POSITIVE LOGITS



0.94

 disponibilités

0.90

DockStyle

0.85

UnsafeEnabled

0.76

 חיצוניים

0.74

Демографія

0.73

kháu

0.72

Controllo

0.69

GraphicsUnit

0.69

 Савезне

0.68

Activations Density 1.687%

technical terms and concepts related to machine learning and statistical estimators

No Comments

No Known Activations