INDEX

Explanations

programming-related keywords and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.64

AndEndTag

-0.47

 basic

-0.46

 direct

-0.42

 سكانية

-0.41

nocześnie

-0.41

новременно

-0.41

 pres

-0.40

umably

-0.40

WebServlet

-0.40

POSITIVE LOGITS

Controllo

0.90

Geplaatst

0.87

 صوتيه

0.80

 HasFactory

0.72

 nakalista

0.71

 Moslem

0.70

Extinguishing

0.69

 InputDecoration

0.67

 autorytatywna

0.66

StreetMap

0.65

Activations Density 0.241%

programming-related keywords and identifiers

No Comments

No Known Activations