INDEX

Explanations

code-related terms and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

uxxxx

-0.60

inquirer

-0.54

AddWithValue

-0.54

putString

-0.54

didSet

-0.54

 gyhoeddwyd

-0.53

BeginInit

-0.53

createCell

-0.53

HttpPut

-0.53

 StatelessWidget

-0.52

POSITIVE LOGITS

VIAF

0.69

fastjson

0.62

 utafitiHapana

0.54

youts

0.54

HtmlAttribute

0.53

 VIAF

0.51

onalds

0.50

 GenerationType

0.50

κτή

0.49

GeneratedMessage

0.49

Activations Density 0.436%

code-related terms and keywords

No Comments

No Known Activations