INDEX

Explanations

words and phrases associated with movement and directionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 amely

-0.33

-0.32

 frek

-0.32

 frequency

-0.31

oarece

-0.30

frequency

-0.29

 estrés

-0.29

 שה

-0.29

 which

-0.28

Кли

-0.27

POSITIVE LOGITS

########.

0.93

 autorytatywna

0.87

+#+

0.81

 ब्रेकडाउन

0.72

OGND

0.70

DockStyle

0.68

 Infórmanos

0.67

原始内容存档于

0.65

Parcelize

0.65

HomeAsUpEnabled

0.65

Activations Density 0.327%

words and phrases associated with movement and directionality

No Comments

No Known Activations