INDEX

Explanations

negative affirmations or denials

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

"No"

np_acts-logits-general · gemini-2.0-flash

No

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

("}\

-0.59

 culturelles

-0.58

ように

-0.57

}\

-0.55

 redor

-0.55

 "\""

-0.54

 Autorizaciones

-0.52

{}\

-0.50

 jeter

-0.50

:\/\/

-0.50

POSITIVE LOGITS

No

1.22

No

1.20

no

1.15

NO

1.13

DockStyle

1.01

Nox

1.00

NO

1.00

 Noyes

0.96

stalgia

0.96

ValueStyle

0.95

Activations Density 0.131%

negative affirmations or denials

"No"

No

No Comments

No Known Activations