INDEX

Explanations

connections and references to ongoing research and reliable information sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

usermodel

-0.71

basicConfig

-0.60

Personendaten

-0.58

XmlAccessorType

-0.57

 pinulongan

-0.56

 Illuminate

-0.56

脚注の使い方

-0.55

AntiForgeryToken

-0.55

 cabins

-0.54

 AssemblyTitle

-0.54

POSITIVE LOGITS

Initializable

0.61

 sourcing

0.54

 sources

0.53

Acqu

0.52

 searches

0.52

úsqueda

0.51

 RestTemplate

0.51

 URLs

0.50

 networking

0.50

ंगे

0.50

Activations Density 0.483%

connections and references to ongoing research and reliable information sources

No Comments

No Known Activations