INDEX

Explanations

descriptive terms that relate to shapes and their characteristics

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

rounded shapes and modifications

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Билгалдахарш

-0.56

writerow

-0.49

scrapy

-0.47

Хьажоргаш

-0.46

 Præ

-0.46

 ocul

-0.45

 getField

-0.45

郎

-0.45

scryfall

-0.45

[]:

-0.45

POSITIVE LOGITS

 Rounded

0.73

 rounded

0.63

homa

0.57

rounded

0.54

wellness

0.54

 Rugged

0.54

 zacht

0.52

 StatelessWidget

0.52

Rounded

0.52

 Fuller

0.52

Activations Density 0.014%

descriptive terms that relate to shapes and their characteristics

rounded shapes and modifications

No Comments

No Known Activations