INDEX

Explanations

words indicating relationships and interactions among people or objects

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

 LoginComponent

-0.63

 BorderRadius

-0.59

visiae

-0.57

 мәкал

-0.57

ertale

-0.56

medriver

-0.55

 فريبيس

-0.55

UpdateCommand

-0.54

theoremstyle

-0.53

enumi

-0.53

POSITIVE LOGITS

XmlEnum

0.56

 betweenstory

0.55

mal

0.47

 ngữ

0.47

енча

0.47

ⓧ

0.46

 yeux

0.44

orphism

0.43

Kind

0.42

={({

0.42

Activations Density 0.607%

words indicating relationships and interactions among people or objects

No Comments

No Known Activations