INDEX

Explanations

references to journaling and self-reflection tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

imageio

-0.61

 scio

-0.55

Datuak

-0.51

reht

-0.50

Geplaatst

-0.50

 Bowser

-0.49

aminan

-0.49

uebe

-0.48

zzer

-0.47

haku

-0.47

POSITIVE LOGITS

 notes

1.31

 note

1.18

 Notes

1.14

notes

1.09

 notebook

1.09

Notes

1.02

 Note

0.99

note

0.99

 notepad

0.97

 notebooks

0.97

Activations Density 0.371%

references to journaling and self-reflection tools

No Comments

No Known Activations