INDEX

Explanations

phrases that indicate suitability and compatibility of products or concepts

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

 falando

-0.52

iestety

-0.50

 שוליים

-0.50

 سكانية

-0.49

meneu

-0.49

 heridos

-0.48

 Hacking

-0.48

OTTEN

-0.48

determined

-0.48

ClientSize

-0.47

POSITIVE LOGITS

XmlType

0.64

findpost

0.63

 suitable

0.56

adaptiveStyles

0.56

 ProtoMessage

0.53

jsii

0.51

 eignet

0.51

 sowohl

0.51

Modules

0.50

 itſelf

0.50

Activations Density 0.206%

phrases that indicate suitability and compatibility of products or concepts

No Comments

No Known Activations