INDEX

Explanations

start and end markers in the text

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

kloped

-0.60

 Jorg

-0.49

God

-0.47

 girl

-0.47

 within

-0.47

Encyklopedia

-0.46

Identyfik

-0.46

тей

-0.46

 also

-0.45

"&

-0.44

POSITIVE LOGITS

oredCriteria

0.78

featureID

0.76

IUrlHelper

0.69

RuleContext

0.69

 հղումներ

0.64

flink

0.64

 ligiloj

0.63

forKey

0.62

 StatefulWidget

0.62

lustre

0.60

Activations Density 0.159%

start and end markers in the text

No Comments

No Known Activations