INDEX

Explanations

mentions of specific individuals and their roles in political contexts

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

Tokens preceding symbols or abbreviations

np_acts-logits-general · gemini-2.0-flash

foreign words and punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

↵

-0.35

-0.34

</tr>

-0.34

↵↵

-0.32

-0.30

POSITIVE LOGITS

Datuak

0.93

parsedMessage

0.89

iſen

0.89

 témoig

0.87

 Geiſt

0.86

 queſta

0.85

 increí

0.85

ðsíða

0.84

 indígen

0.83

niſſe

0.82

Activations Density 2.950%

mentions of specific individuals and their roles in political contexts

Tokens preceding symbols or abbreviations

foreign words and punctuation

No Comments

No Known Activations