INDEX

Explanations

phrases indicating restrictions or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

abetes

-0.70

}\]

-0.63

__*/

-0.61

ientôt

-0.61

 aika

-0.59

axter

-0.59

υτό

-0.58

IUrlHelper

-0.58

daß

-0.58

انيف

-0.58

POSITIVE LOGITS

 beschränkt

0.54

 confined

0.53

 disambiguazione

0.48

 merely

0.47

 limited

0.46

 confines

0.46

*:

0.45

confined

0.44

แค่

0.44

あく

0.44

Activations Density 0.337%

phrases indicating restrictions or limitations

No Comments

No Known Activations