INDEX

Explanations

markers indicating the beginning of a section or new content

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ioutil

-0.79

nyc

-0.72

Архівовано

-0.72

ADELPHIA

-0.67

 Schles

-0.67

🏾

-0.65

 lccn

-0.64

 Soho

-0.64

ValueStyle

-0.64

 Philadelphia

-0.63

POSITIVE LOGITS

脚注の使い方

0.66

 Amish

0.64

Grandpa

0.63

///</

0.63

Iowa

0.61

 motel

0.60

 rurales

0.60

FFA

0.59

 rodeo

0.59

 >=",

0.59

Activations Density 0.298%

markers indicating the beginning of a section or new content

No Comments

No Known Activations