INDEX

Explanations

phrases that prompt readers to visualize or envision scenarios

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 StatefulWidget

-0.70

providedIn

-0.63

-0.62

bouncycastle

-0.62

τως

-0.61

 referenties

-0.61

 tông

-0.60

cientos

-0.59

Datuak

-0.57

strix

-0.57

POSITIVE LOGITS

 IMAG

1.40

 imagining

1.38

 Imagine

1.34

 imagine

1.33

 imagines

1.30

Imagin

1.30

 Imagination

1.29

Imagine

1.28

 imagin

1.27

 Imagin

1.25

Activations Density 0.080%

phrases that prompt readers to visualize or envision scenarios

No Comments

No Known Activations