INDEX

Explanations

file formats and extensions, particularly image-related ones

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

File names ending in ".png" or ".js"

np_acts-logits-general · gemini-2.0-flash

file extensions

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

Compar

-0.55

sina

-0.55

'}>

-0.54

เบ

-0.53

gand

-0.53

 Neuk

-0.51

 Chwiliwch

-0.51

 }}}{

-0.50

%";

-0.50

ability

-0.50

POSITIVE LOGITS

EDEFAULT

0.69

IntoConstraints

0.69

 Obrador

0.69

 виправивши

0.63

々木

0.61

omitempty

0.58

 supposing

0.57

 Roskov

0.56

 חיצוניים

0.55

่านั้น

0.55

Activations Density 0.139%

file formats and extensions, particularly image-related ones

File names ending in ".png" or ".js"

file extensions

No Comments

No Known Activations