INDEX

Explanations

bullet points and lists of topics or features

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ksjon

-0.82

 --}}

-0.81

脚注の使い方

-0.80

innig

-0.79

zwe

-0.78

 Luch

-0.78

 Jacob

-0.75

}$$

-0.74

Manbalar

-0.73

OfBirth

-0.72

POSITIVE LOGITS

••

1.47

.•

1.36

•••

1.36

•

1.26

••••

1.26

°•

1.25

er

1.22

~•

1.11

)•

1.00

 ••

0.94

Activations Density 0.064%

bullet points and lists of topics or features

No Comments

No Known Activations