INDEX

Explanations

references to conferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

disposed

-0.68

 utilis

-0.67

 evit

-0.64

 numberWith

-0.63

 προς

-0.63

 pasti

-0.61

 SOIL

-0.60

otus

-0.60

 SPECIES

-0.60

صاص

-0.60

POSITIVE LOGITS

 conferences

1.62

 Conferences

1.51

 conference

1.50

 Conference

1.48

Conference

1.38

conference

1.29

 CONFERENCE

1.28

 Conférence

1.10

konferenz

1.09

 Konferenz

1.05

Activations Density 0.063%

references to conferences

No Comments

No Known Activations

references to conferences

No Comments

No Known Activations