INDEX

Explanations

key terms related to health and safety topics

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

 دیکھیے

-0.78

 autorytatywna

-0.71

OGND

-0.69

InjectAttribute

-0.62

 defaultstate

-0.62

makeConstraints

-0.62

bilang

-0.61

expandindo

-0.60

Referencie

-0.60

 ujednoznacz

-0.60

POSITIVE LOGITS

iest

1.14

 safest

1.09

 happiest

1.09

 freshest

1.08

ariest

1.07

 healthiest

1.07

liest

1.04

 warmest

1.04

iniest

1.03

 best

1.01

Activations Density 0.252%

key terms related to health and safety topics

No Comments

No Known Activations