INDEX

Explanations

specific names and locations related to legal cases or legislative contexts

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

 Roskov

-0.92

horabuena

-0.90

存于互联网档案馆

-0.90

Fid

-0.89

issory

-0.87

ConstraintMaker

-0.86

centralwidget

-0.85

batore

-0.85

raszam

-0.85

+:+

-0.81

POSITIVE LOGITS

 Decatur

0.84

ि

0.76

 Tome

0.71

BER

0.70

 Koll

0.70

pia

0.69

Tome

0.69

McKin

0.69

assin

0.69

Cud

0.69

Activations Density 1.420%

specific names and locations related to legal cases or legislative contexts

No Comments

No Known Activations