INDEX

Explanations

mentions of various sports and sports-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 للاسماء

-0.96

 Luglio

-0.85

 maternelle

-0.85

ssysteme

-0.84

 Necklace

-0.84

gdala

-0.80

 sawmill

-0.79

 Knives

-0.79

Zeneca

-0.78

 necklaces

-0.77

POSITIVE LOGITS

 sports

2.41

 Sports

2.20

 sport

2.17

Sports

2.06

 Sport

2.02

sports

2.01

 SPORT

1.93

Sport

1.93

sport

1.83

 SPORTS

1.82

Activations Density 0.029%

mentions of various sports and sports-related activities

No Comments

No Known Activations