INDEX

Explanations

the beginning of meaningful sections or paragraphs in text

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

bound word followed by verb

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 tartalomajánló

-0.47

 Floren

-0.44

 Ston

-0.43

 successivo

-0.43

ureusement

-0.42

 Pang

-0.42

 fates

-0.42

 erfaring

-0.41

Aún

-0.41

ńska

-0.41

POSITIVE LOGITS

 ModelExpression

0.98

CreateModel

0.78

 ISNI

0.71

modelBuilder

0.71

formik

0.69

 protoimpl

0.68

ModelAttribute

0.66

Demografie

0.65

cshtml

0.65

 AspNetCore

0.65

Activations Density 0.002%

the beginning of meaningful sections or paragraphs in text

bound word followed by verb

No Comments

No Known Activations