INDEX

Explanations

scientific terminology related to statistical models and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 roulant

-0.69

abetes

-0.67

bip

-0.63

eaways

-0.63

 Guadal

-0.60

 Harlow

-0.59

embatan

-0.59

 Kear

-0.59

adone

-0.59

 htmlFor

-0.59

POSITIVE LOGITS

SGS

0.91

Hubert

0.85

 Hubert

0.84

verwijspagina

0.81

 Lagos

0.78

 Clément

0.76

 lenker

0.76

hdessä

0.74

CSD

0.74

 memes

0.71

Activations Density 9.406%

scientific terminology related to statistical models and their properties

No Comments

No Known Activations