INDEX

Explanations

references to networks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 mourut

-0.96

 réfugi

-0.93

 hâte

-0.92

 colorés

-0.90

 répondit

-0.88

 titolata

-0.86

 feroit

-0.85

GLS

-0.85

 auroit

-0.84

 meurt

-0.84

POSITIVE LOGITS

 networks

1.27

 network

1.20

 Network

1.06

 networking

1.03

Network

1.01

networks

0.96

network

0.96

 Networks

0.92

Networks

0.88

NETWORK

0.87

Activations Density 0.029%

references to networks

No Comments

No Known Activations