INDEX

Explanations

instances of the word "walk" or related variations in the text

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

 laiton

-0.88

 Brenner

-0.83

essentiel

-0.83

 navideños

-0.82

 Darmstadt

-0.81

 suprême

-0.79

 Anya

-0.79

 religiosos

-0.79

íso

-0.78

 jäsen

-0.77

POSITIVE LOGITS

 walk

1.67

 WALK

1.59

 Walk

1.56

walk

1.55

 walks

1.49

 walking

1.48

Walk

1.48

 Walks

1.46

 walked

1.45

 Walking

1.42

Activations Density 0.043%

instances of the word "walk" or related variations in the text

No Comments

No Known Activations