INDEX

Explanations

words related to negative outcomes or situations

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

jednoc

-0.76

PhysRevD

-0.73

 connexes

-0.72

rijke

-0.72

IUrlHelper

-0.70

GOTREF

-0.70

 Laing

-0.68

 Bourgoin

-0.68

ίκη

-0.66

cupertino

-0.66

POSITIVE LOGITS

 worse

1.29

Worse

1.22

 Worse

1.17

 worst

1.14

 Worst

1.07

worse

1.07

bad

1.05

BAD

1.05

Bad

1.02

Worst

1.02

Activations Density 0.147%

words related to negative outcomes or situations

No Comments

No Known Activations