INDEX

Explanations

references to edges within graphs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 pitié

-0.97

 bienvenue

-0.85

достатки

-0.79

 Harlequin

-0.75

 wikihow

-0.75

abstractmethod

-0.74

 Timberlake

-0.73

 Lowry

-0.73

 Kaly

-0.73

lioz

-0.72

POSITIVE LOGITS

AGE

1.09

ge

1.06

ages

1.06

ges

1.03

Ge

1.01

tage

0.97

GE

0.96

GES

0.96

 Hage

0.96

Ge

0.96

Activations Density 0.138%

references to edges within graphs

No Comments

No Known Activations