INDEX

Explanations

references to flat or level surfaces

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

"flat"

np_acts-logits-general · gemini-2.0-flash

flatflat list

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

__':

-1.00

 CreateTagHelper

-0.97

tagHelperRunner

-0.86

__":

-0.84

MeasureSpec

-0.83

 HasFactory

-0.82

 StringTokenizer

-0.82

__':

-0.81

</>

-0.80

FormTagHelper

-0.80

POSITIVE LOGITS

 flat

1.26

 Flat

1.18

flat

1.13

 FLAT

1.11

Flat

1.10

 Flats

1.08

 flats

1.08

FLAT

1.07

flats

0.97

 plat

0.95

Activations Density 0.140%

references to flat or level surfaces

"flat"

flatflat list

No Comments

No Known Activations