INDEX

Explanations

mentions of locations, specifically cities in California

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

 Roskov

-1.30

InjectAttribute

-1.18

 propOrder

-1.17

 tartalomajánló

-1.14

 itſelf

-1.11

WebVitals

-1.10

 Palembang

-1.08

 myſelf

-1.08

VIAF

-1.05

ItemBackground

-1.04

POSITIVE LOGITS

San

2.47

San

2.23

san

1.99

san

1.87

SAN

1.86

SAN

1.73

 Сан

1.28

 Sanford

1.09

ssan

1.05

 Sandi

1.03

Activations Density 0.054%

mentions of locations, specifically cities in California

No Comments

No Known Activations