INDEX

Explanations

references to geographic locations and names related to historical events or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Erickson

-0.69

pous

-0.68

 Rosen

-0.67

þ

-0.67

 Martino

-0.67

findpost

-0.67

-0.65

Cid

-0.64

 Kass

-0.63

aging

-0.62

POSITIVE LOGITS

Bout

0.90

Faw

0.90

Lola

0.89

 Prou

0.88

 Margot

0.86

 Wilshire

0.85

 Clough

0.85

 Pires

0.85

assium

0.84

 Magdalene

0.84

Activations Density 1.878%

references to geographic locations and names related to historical events or figures

No Comments

No Known Activations