INDEX

Explanations

code comments and license information

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

Code comments and related symbols

np_acts-logits-general · gemini-2.0-flash

code comments and documentation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 تضيفلها

-0.52

Portail

-0.49

 poffe

-0.46

AndEndTag

-0.46

 estekak

-0.45

Hochspringen

-0.45

 فريبيس

-0.44

 myſelf

-0.44

 nakalista

-0.42

 occafion

-0.41

POSITIVE LOGITS

 CreateTagHelper

0.47

 defaultstate

0.40

 transfieras

0.39

 hObject

0.39

 Toxicology

0.39

 Jede

0.39

 gradova

0.37

sproz

0.37

 Karriere

0.36

สง

0.36

Activations Density 0.084%

code comments and license information

Code comments and related symbols

code comments and documentation

No Comments

No Known Activations