INDEX

Explanations

references to options or alternative choices in a document

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

 bezeichneter

-0.61

CrossRef

-0.60

writeField

-0.56

SerializedName

-0.48

انيف

-0.47

XmlAccessorType

-0.47

xDB

-0.47

hline

-0.45

}{*}{}

-0.45

signable

-0.44

POSITIVE LOGITS

 Options

1.42

 options

1.36

 OPTION

1.20

 option

1.19

options

1.15

 OPTIONS

1.13

 Choices

1.09

 onOptions

1.07

 Option

1.06

OPTION

1.05

Activations Density 0.184%

references to options or alternative choices in a document

No Comments

No Known Activations