INDEX

Explanations

references to published research and systematic literature reviews

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

"key" or "search" terms

np_acts-logits-general · gemini-2.0-flash

search terms and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 considérons

-0.57

 getInstance

-0.55

 Detalles

-0.52

ReusableCell

-0.52

SharedDtor

-0.51

ANDUM

-0.50



-0.50

Życiorys

-0.50

PRNewswire

-0.50

tvguidetime

-0.50

POSITIVE LOGITS

 keywords

1.93

 tags

1.80

 keyword

1.74

tag

1.71

 Keywords

1.51

 Tags

1.50

tags

1.50

Keywords

1.44

Tag

1.43

keywords

1.41

Activations Density 0.390%

references to published research and systematic literature reviews

"key" or "search" terms

search terms and keywords

No Comments

No Known Activations