INDEX

Explanations

phrases related to positioning or physical placement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

RenderAtEndOf

-0.66

TargetException

-0.66

 lenker

-0.57

 nucle

-0.55

findpost

-0.54

cepan

-0.54

:✨

-0.54

 endblock

-0.53

PMailer

-0.52

orsese

-0.51

POSITIVE LOGITS

 atop

0.75

__":

0.62

 perched

0.59

 Acrobat

0.58

modelBuilder

0.58

 aerial

0.58

 inverted

0.57

 aloft

0.57

__':

0.56

 inversion

0.55

Activations Density 0.461%

phrases related to positioning or physical placement

No Comments

No Known Activations