INDEX

Explanations

mentions of specific examples or cases along with their details or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

endphp

-0.81

ArgumentParser

-0.75

 متعلقه

-0.71

 ModelExpression

-0.70

">//

-0.65

UserScript

-0.64

routeProvider

-0.63

 CreateTagHelper

-0.63

+:+

-0.62

parsedMessage

-0.62

POSITIVE LOGITS

 pictured

0.76

 shown

0.62

一見

0.60

Notice

0.50

 ComVisible

0.49

shown

0.49

pictured

0.48

ese

0.48

 picture

0.48

👆

0.48

Activations Density 0.716%

mentions of specific examples or cases along with their details or explanations

No Comments

No Known Activations