INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 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

 Monfieur

-0.88

 fubject

-0.85

 myſelf

-0.84

 feroit

-0.79

 uſed

-0.77

 themſelves

-0.75

 himſelf

-0.75

iestety

-0.74

 auroit

-0.73

 beſt

-0.71

POSITIVE LOGITS

 feeling

0.99

 vibe

0.89

 feel

0.84

feel

0.80

feeling

0.79

 sense

0.77

 felt

0.76

 feels

0.75

Feel

0.75

 Feel

0.72

Activations Density 0.050%

No Comments

No Known Activations