INDEX

Explanations

proper nouns, particularly names of people and notable entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

setGravity

-0.49

DataURL

-0.47

cal

-0.44

artig

-0.43

ENZO

-0.43

 muka

-0.42

 Apare

-0.42

álló

-0.42

τους

-0.42

⇀

-0.41

POSITIVE LOGITS

AndEndTag

0.73

featureID

0.73

 المعيارى

0.66

 pinulongan

0.63

 صوتيه

0.63

 aDecoder

0.62

 ddelweddau

0.59

ंदीखरीदारी

0.59

typeorm

0.56

 onCancelled

0.56

Activations Density 0.440%

proper nouns, particularly names of people and notable entities

No Comments

No Known Activations