INDEX

Explanations

phrases indicating primary subjects or main ideas in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 CreateTagHelper

-0.55

 InputDecoration

-0.54

 BorderRadius

-0.53

 Lightboxes

-0.51

 refusé

-0.51

اهرة

-0.50

 tôt

-0.50

titleMargin

-0.49

 früh

-0.48

GOTREF

-0.48

POSITIVE LOGITS

 main

1.05

 MAIN

1.01

 Main

1.00

Main

0.96

 principale

0.93

MAIN

0.91

 principal

0.88

getMain

0.87

main

0.86

 Haupt

0.85

Activations Density 0.270%

phrases indicating primary subjects or main ideas in a text

No Comments

No Known Activations