INDEX

Explanations

phrases that indicate availability or inclusivity in regulatory or system contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Sometimes

-0.43

 tartalomajánló

-0.42

PropertyChanging

-0.42

enee

-0.42

nąć

-0.40

</thead>

-0.40

viaf

-0.40

Sometimes

-0.39

TagHelper

-0.39

melli

-0.39

POSITIVE LOGITS

all

2.68

 semua

2.36

 todas

2.31

 tutte

2.27

 всех

2.25

 everyone

2.22

 everything

2.19

 every

2.17

everything

2.14

すべての

2.13

Activations Density 2.001%

phrases that indicate availability or inclusivity in regulatory or system contexts

No Comments

No Known Activations