INDEX

Explanations

questions and discussions about DNS records and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PyExc

-0.54

StoryboardSegue

-0.53

 EdgeInsets

-0.53

asthan

-0.50

TintMode

-0.50

pyx

-0.48

msgTypes

-0.48

ession

-0.46

tilhe

-0.46

ссажи

-0.46

POSITIVE LOGITS

 Domains

1.08

 Domain

1.08

 domain

1.03

 domains

1.00

 hosting

0.96

 Hosting

0.95

DNS

0.93

 Host

0.91

 host

0.90

Domain

0.90

Activations Density 0.265%

questions and discussions about DNS records and configurations

No Comments

No Known Activations