INDEX

Explanations

reference to figures or illustrations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

cshtml

-0.63

 ModelExpression

-0.54

ArgsConstructor

-0.52

WriteLiteral

-0.52

GroupLayout

-0.52

Биография

-0.52

 Normdatei

-0.51

+#+

-0.50

GIVEREF

-0.50

 GenerationType

-0.50

POSITIVE LOGITS

 preocupes

0.66

 newOwner

0.65

ArrowToggle

0.64

 automatiques

0.63

 بتاريخ

0.62

 Спо

0.60

 conformément

0.60

webElementXpaths

0.60

Personendaten

0.60

Tikang

0.60

Activations Density 0.193%

reference to figures or illustrations in the text

No Comments

No Known Activations