INDEX

Explanations

patterns of structured data or formatted content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

SaveChangesAsync

-0.79

 resourceCulture

-0.72

GEBURTSDATUM

-0.72

 Мексичка

-0.71

Jeografia

-0.71

 LoggerFactory

-0.66

Portály

-0.65

WireFormatLite

-0.65

RetentionPolicy

-0.65

Sucesor

-0.61

POSITIVE LOGITS

2.28

([

2.15

,[

2.10

{[

2.09

$[

2.07

-[

2.06

:[

2.06

=[

1.97

.[

1.97

([

1.95

Activations Density 0.542%

patterns of structured data or formatted content

No Comments

No Known Activations