INDEX

Explanations

technical terms and phrases related to networking or computer architecture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

WithIOException

-0.59

 tartalomajánló

-0.47

msgTypes

-0.47

featureID

-0.46

 quirúrg

-0.46

IndentedString

-0.45

плуата

-0.44

ulemon

-0.43

liceerd

-0.43

nodoc

-0.43

POSITIVE LOGITS

WhereInput

0.46

 laptop

0.46

ClCompile

0.44

 TMPro

0.43

antle

0.43

 abra

0.42

 насељу

0.42

 resourceCulture

0.41

 jPanel

0.41

lectual

0.40

Activations Density 3.051%

technical terms and phrases related to networking or computer architecture

No Comments

No Known Activations