INDEX

Explanations

expressions of personal opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 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

ſelf

-0.59

 purpoſe

-0.53

 ſch

-0.52

 faſt

-0.51

 auffi

-0.51

 ſind

-0.50

Intern

-0.50

 houſe

-0.50

 ſever

-0.50

 himſelf

-0.49

POSITIVE LOGITS

 opinion

1.59

 Opinion

1.41

 opinions

1.35

Opinion

1.32

opinion

1.30

 Opinions

1.27

 OPINION

1.24

 opinión

1.23

Opinions

1.14

 opinião

1.11

Activations Density 0.371%

expressions of personal opinions

No Comments

No Known Activations