INDEX

Explanations

terms related to legal and medical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 staff

-0.50

 Staff

-0.48

Staff

-0.46

íqu

-0.45

 himself

-0.43

staff

-0.39

туа

-0.38

fxml

-0.37

招

-0.37

 италья

-0.37

POSITIVE LOGITS

verwijspagina

0.89



0.89

 BoxDecoration

0.79

دانشنامهٔ

0.79

 createStore

0.78

 '\\;'

0.78

formik

0.75

rungsseite

0.73

 disambiguazione

0.73

Parcelize

0.72

Activations Density 2.060%

terms related to legal and medical concepts

No Comments

No Known Activations