INDEX

Explanations

elements related to societal roles and responsibilities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

таратура

-0.43

Jîn

-0.39

わかります

-0.38

Билгалдахарш

-0.37

aarrggbb

-0.36

UnusedPrivate

-0.35

agisse

-0.35

 ब्रेकडाउन

-0.34

BURN

-0.34

easier

-0.34

POSITIVE LOGITS

 للاسماء

0.58

SBATCH

0.55

 дописавши

0.52

webElement

0.51

########.

0.50

</thead>

0.46

出版年

0.43

tură

0.43

 ddelweddau

0.43

thâu

0.42

Activations Density 0.987%

elements related to societal roles and responsibilities

No Known Activations