INDEX

Explanations

mentions of different types of networks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 réfugi

-1.01

 mourut

-0.96

 feroit

-0.94

 réaliste

-0.91

 auroit

-0.91

 démocr

-0.90

 colorés

-0.90

 pouvoit

-0.89

 pitié

-0.87

 estético

-0.86

POSITIVE LOGITS

 network

1.52

 networks

1.50

 Network

1.32

 networking

1.21

network

1.20

Network

1.20

networks

1.18

 Networks

1.15

NETWORK

1.14

Networks

1.09

Activations Density 0.056%

mentions of different types of networks

No Comments

No Known Activations