INDEX

Explanations

proper nouns, particularly names and titles in a scientific context

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

names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 ویکی‌پدی

-0.91

featureID

-0.83

 autorytatywna

-0.76

yym

-0.72

webElementXpaths

-0.70

Spoljašnje

-0.69

aarrggbb

-0.69

 queſta

-0.69

 Infórmanos

-0.68

 Wikimedijinoj

-0.68

POSITIVE LOGITS

);

0.38

).

0.35

Thank

0.33

 Group

0.32

↵↵

0.32

↵

0.32

];

0.31

 Davidson

0.31

San

0.31

<eos>

0.31

Activations Density 0.002%

proper nouns, particularly names and titles in a scientific context

names and titles

No Comments

No Known Activations