INDEX

Explanations

references to dragons and dragon-related concepts

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

dragons

np_acts-logits-general · gemini-2.0-flash

dragon, Dragon, dragons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 endblock

-0.48

 بيها

-0.43

-------

-0.41

rensa

-0.40

MockMvc

-0.38

 ब्रेकडाउन

-0.36

cshtml

-0.36

AndEndTag

-0.36

 otomatig

-0.35

=$?

-0.35

POSITIVE LOGITS

 dragon

1.42

 Dragon

1.31

 dragons

1.24

Dragon

1.23

 DRAGON

1.14

 Dragons

1.11

dragon

1.10

Dragons

1.02

🐉

0.99

🐲

0.98

Activations Density 0.053%

references to dragons and dragon-related concepts

dragons

dragon, Dragon, dragons

No Comments

No Known Activations