INDEX

Explanations

terms associated with academic programs and data-related expertise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ParallelGroup

-1.42

ⓧ

-1.39

")));

-1.39

SequentialGroup

-1.33

fjspx

-1.32

 ***!

-1.32

SourceChecksum

-1.29

Rüyada

-1.27

AccessorTable

-1.24

AndEndTag

-1.24

POSITIVE LOGITS

and

0.83

0.73

but

0.54

0.52

 asemenea

0.50

0.42

и

0.41

 medesimo

0.39

or

0.39

etc

0.39

Activations Density 7.963%

terms associated with academic programs and data-related expertise

No Comments

No Known Activations