INDEX

Explanations

words related to living or life experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 others

-0.54

ünster

-0.53

-0.50

catid

-0.49

 Falcons

-0.49

 Schmidt

-0.49

 Peterson

-0.48

<bos>

-0.48

 حسن

-0.48

 Anderson

-0.47

POSITIVE LOGITS

Living

0.85

living

0.85

 living

0.85

 Living

0.79

 LIVING

0.78

Live

0.76

 Lived

0.75

LIVING

0.75

VIAF

0.75

 Live

0.74

Activations Density 0.074%

words related to living or life experiences

No Comments

No Known Activations