INDEX

Explanations

occurrences of programming-related keywords and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 HasFactory

-0.97

IonicModule

-0.77

IVEREF

-0.73

 tartalomajánló

-0.70

inheritdoc

-0.68

ionView

-0.67

ulipas

-0.65

onOptions

-0.65

 ويكيپيديا

-0.64

nalités

-0.64

POSITIVE LOGITS

import

0.74

 nahilalakip

0.70

imports

0.60

 autorytatywna

0.56

 particularly

0.53

 import

0.53

 especially

0.52

 disponibilités

0.51

 InputDecoration

0.51

 للمعارف

0.51

Activations Density 0.036%

occurrences of programming-related keywords and constructs

No Comments

No Known Activations