INDEX

Explanations

references to geographic locations, specifically North-related places and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

LEncoder

-0.98

GEBURTSDATUM

-0.92

 ModelRenderer

-0.91

 Pacer

-0.90

 وتسجيلات

-0.88

addGap

-0.82

Remo

-0.81

 Lugano

-0.81

ReusableCell

-0.81

ModelSerializer

-0.80

POSITIVE LOGITS

 North

1.25

north

1.12

NORTH

1.11

North

1.05

 north

1.03

south

1.03

 NORTH

1.01

 South

1.00

 Noth

0.92

 south

0.92

Activations Density 0.058%

references to geographic locations, specifically North-related places and entities

No Comments

No Known Activations