INDEX

Explanations

performing actions that indicate nervousness or fidgeting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 suffit

-0.47

 responsabilité

-0.46

bil

-0.45

حم

-0.44

Begriffsklä

-0.44

 hanem

-0.43

 scaled

-0.43

再来

-0.43

неопр

-0.42

 oseb

-0.42

POSITIVE LOGITS

MessageTagHelper

0.80

 idly

0.68

 autorytatywna

0.66

PreferredItem

0.66

XtraEditors

0.66

 initComponents

0.65

IBOutlet

0.64

 fidget

0.63

 Hopf

0.63

XtraGrid

0.63

Activations Density 0.171%

performing actions that indicate nervousness or fidgeting

No Comments

No Known Activations