INDEX

Explanations

references to 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 @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 réfugi

-0.99

 colorés

-0.96

 feroit

-0.94

 mourut

-0.94

 pouvoit

-0.93

 hâte

-0.93

 démocr

-0.91

 auroit

-0.91

 titolata

-0.90

érfi

-0.89

POSITIVE LOGITS

 network

1.84

 networks

1.78

 Network

1.58

network

1.52

Network

1.47

 networking

1.44

 Networks

1.38

networks

1.38

NETWORK

1.36

 NETWORK

1.32

Activations Density 0.045%

references to different types of networks

No Comments

No Known Activations

references to different types of networks

No Comments

No Known Activations