INDEX

Explanations

personal pronouns and contractions, indicating a focus on individual perspectives and experiences

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

‘

-1.53

“

-1.52

’

-1.33

”

-1.28

.’

-1.26

’,

-1.26

’.

-1.25

=”

-1.24

.”

-1.19

,’

-1.13

POSITIVE LOGITS

 Jefus

1.38

 purpoſe

1.37

 poffible

1.30

Efq

1.30

 ainfi

1.29

 ſtate

1.28

 Majefty

1.26

 againſt

1.24

 houſe

1.23

 myſelf

1.22

Activations Density 0.602%

personal pronouns and contractions, indicating a focus on individual perspectives and experiences

No Comments

No Known Activations