INDEX

Explanations

references to visual elements or figures

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

References or citations (e.g., [1], [2])

np_acts-logits-general · gemini-2.0-flash

citations and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

说着

-0.31

 reda

-0.31

bootstrapcdn

-0.29

وسط

-0.28

 medio

-0.28

 incl

-0.28

 rather

-0.28

 pengaturan

-0.27

もしれない

-0.26

par

-0.26

POSITIVE LOGITS

 disambiguazione

0.88

parsedMessage

0.75

DockStyle

0.72

 popoli

0.71

BibitemShut

0.70

 Administrativna

0.69

astify

0.68

expandindo

0.68

rungsseite

0.67

 препратки

0.67

Activations Density 0.988%

references to visual elements or figures

References or citations (e.g., [1], [2])

citations and references

No Comments

No Known Activations