INDEX

Explanations

terms that describe peculiarity or strangeness

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

ztály

-0.46

@[+][

-0.45

 referenties

-0.45

accharide

-0.43

essentiel

-0.42

createCanvas

-0.42

 responsabile

-0.41

дию

-0.41

olars

-0.41

êque

-0.40

POSITIVE LOGITS

 étrange

1.02

 strange

1.01

 Strange

1.01

strange

1.00

odd

0.98

 Weird

0.96

Strange

0.95

Weird

0.94

 Unusual

0.93

 coincidence

0.92

Activations Density 0.185%

terms that describe peculiarity or strangeness

No Comments

No Known Activations