INDEX

Explanations

references to AWS IAM (Identity and Access Management) roles and their permissions in policy documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

numerusform

-0.64

zeczy

-0.60

hoek

-0.55

 Korn

-0.55

omla

-0.54

仰

-0.53

Ral

-0.52

 ballast

-0.52

Korn

-0.51

CodedInputStream

-0.49

POSITIVE LOGITS

 Amazon

1.69

Amazon

1.52

 amazon

1.44

 AMAZON

1.32

amazon

1.18

AWS

1.16

AMAZ

1.10

 Amaz

1.09

AWS

1.07

 Kindle

1.02

Activations Density 0.266%

references to AWS IAM (Identity and Access Management) roles and their permissions in policy documents

No Comments

No Known Activations