INDEX

Explanations

keywords and expressions related to programming structures and logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

faker

-0.57

 iprot

-0.54

EnableWeb

-0.53

 lapis

-0.52

NameInMap

-0.51

picasso

-0.51

 وتسجيلات

-0.50

 barber

-0.50

Ips

-0.50

fjspx

-0.49

POSITIVE LOGITS

CppMethod

0.54

tvguidetime

0.53

𝟹

0.51

 StyleSheet

0.49

 kháng

0.49

0.48

yung

0.47

idosis

0.46

alucía

0.45

 للمعارف

0.45

Activations Density 0.070%

keywords and expressions related to programming structures and logic

No Comments

No Known Activations