INDEX

Explanations

programmatic control structures and keywords related to loops in coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 TextInputType

-0.63

OGND

-0.63

eradish

-0.60

Portail

-0.60

 виправивши

-0.59

Datuak

-0.59

 שוליים

-0.55

 itſelf

-0.54

TagMode

-0.53

esModule

-0.53

POSITIVE LOGITS

 loop

1.36

loop

1.23

 Loop

1.15

 loops

1.12

Loop

1.10

 while

1.08

 Loops

1.03

循环

1.03

loops

1.02

 looping

1.00

Activations Density 0.716%

programmatic control structures and keywords related to loops in coding

No Comments

No Known Activations