INDEX

Explanations

references to scientific methodologies or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 BoxFit

-0.60

oa̍t

-0.58

 betweenstory

-0.58

endregion

-0.56

 AssemblyCulture

-0.56

QtWidgets

-0.52

 '\\;'

-0.52

endforeach

-0.50

 AttributeSet

-0.49

setVerticalGroup

-0.49

POSITIVE LOGITS

 pertama

0.82

 first

0.81

first

0.75

 firstly

0.75

①

0.72

❶

0.71

⒈

0.67

①

0.67

第一

0.67

 eerste

0.67

Activations Density 0.491%

references to scientific methodologies or results

No Comments

No Known Activations