INDEX

Explanations

references to exercise and physical activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BeginContext

-0.77

contentLoaded

-0.77

 EconPapers

-0.72

mberto

-0.70

werfer

-0.64

 ujednoznacz

-0.63

chila

-0.62

onedDateTime

-0.61

Javadoc

-0.59

CEEDED

-0.58

POSITIVE LOGITS

 exercises

0.76

 Exercises

0.64

Exercises

0.63

 EXERCISE

0.62

Dunn

0.62

 regimen

0.61

 regimens

0.60

exercises

0.57

 regime

0.57

 routines

0.56

Activations Density 0.120%

references to exercise and physical activity

No Comments

No Known Activations