INDEX

Explanations

phrases related to processes and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ways

-0.75

FormTagHelper

-0.63

way

-0.62

PerformLayout

-0.61

 mahdol

-0.60

 mukana

-0.58

طريقة

-0.56

enetrable

-0.55

 aikana

-0.54

TableField

-0.54

POSITIVE LOGITS

 ***!

0.87

 sich

0.83

 szóci

0.75

RVA

0.75

WebServlet

0.72

 ModelExpression

0.71

НИК

0.70

')

0.69

]>

0.69

 HMRC

0.69

Activations Density 0.029%

phrases related to processes and actions

No Comments

No Known Activations