INDEX

Explanations

technical terms and function calls related to programming and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 bershka

-0.50

Portály

-0.49

ēc

-0.47

dome

-0.46

 ligiloj

-0.46

 Impulse

-0.46

 trion

-0.45

 makl

-0.45

otras

-0.45

bok

-0.44

POSITIVE LOGITS

1.66

1.42

(&

1.41

(&

1.25

)&

1.25

,&

1.23

=&

1.13

>(&

1.12

&_

1.12

}&

1.12

Activations Density 0.154%

technical terms and function calls related to programming and data processing

No Comments

No Known Activations