INDEX

Explanations

phrases indicating action or removal

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

"off"

np_acts-logits-general · gemini-2.0-flash

off

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Winaray

-0.92

Parcelize

-0.92

ESM

-0.87

OGND

-0.85

Życiorys

-0.83

Personensuche

-0.82

SqlClient

-0.80

 Forumite

-0.79

 itſelf

-0.77

Pratique

-0.76

POSITIVE LOGITS

Off

1.57

off

1.54

Off

1.42

OFF

1.42

off

1.41

OFF

1.16

offs

1.11

 offs

1.01

オフ

0.85

 オフ

0.75

Activations Density 0.077%

phrases indicating action or removal

"off"

off

No Comments

No Known Activations