INDEX

Explanations

words related to sweetness or sweet flavors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 propOrder

-1.16

ModelAdmin

-1.16

bootstrapcdn

-1.10

 myſelf

-1.10

httphttps

-1.06

abestanden

-1.02

Efq

-1.01

 ویکی‌پدیای

-1.00

ViewFeatures

-0.99

.*")]

-0.98

POSITIVE LOGITS

 sweet

1.83

 Sweet

1.79

Sweet

1.74

sweet

1.69

 SWEET

1.61

SWEET

1.60

 sweetness

1.20

 sweeter

1.19

 sweetest

1.18

 Sweets

1.09

Activations Density 0.038%

words related to sweetness or sweet flavors

No Comments

No Known Activations