INDEX

Explanations

attributes related to spells or abilities in a fantasy context

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

Strings after a colon

np_acts-logits-general · gemini-2.0-flash

tokens like : ) & or duration instant

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 totiž

-0.56

 nämlich

-0.56

 namelijk

-0.51

 infatti

-0.50

 nemlig

-0.47

 navíc

-0.46

тербург

-0.45

 bowiem

-0.44

alım

-0.43

Поэтому

-0.42

POSITIVE LOGITS

 None

1.39

 none

1.32

 Varies

1.31

 Unknown

1.28

None

1.27

 unknown

1.24

none

1.22

Unknown

1.20

unknown

1.15

 NONE

1.13

Activations Density 0.914%

attributes related to spells or abilities in a fantasy context

Strings after a colon

tokens like : ) & or duration instant

No Comments

No Known Activations