INDEX

Explanations

guidelines and recommendations related to emergency risk communication and preparedness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 remembers

-0.53

 contigo

-0.53

 AssemblyVersion

-0.51

spli

-0.50

jfree

-0.50

 arred

-0.48

Honor

-0.47

pearance

-0.47

 scoperto

-0.46

 quitar

-0.46

POSITIVE LOGITS

 policy

1.38

 policies

1.16

 policymakers

1.15

policy

1.10

 Policy

1.02

 POLICY

0.98

Policy

0.97

 governance

0.94

 institutional

0.91

POLICY

0.90

Activations Density 0.679%

guidelines and recommendations related to emergency risk communication and preparedness

No Comments

No Known Activations