INDEX

Explanations

numerical values, particularly measurements and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 بيها

-0.75

ंदीखरीदारी

-0.64

 تكبرها

-0.59

 linkovi

-0.57

 архивлан

-0.57

iterranée

-0.57

InputTagHelper

-0.56

AddAttribute

-0.56

abestanden

-0.54

uxxxx

-0.54

POSITIVE LOGITS

/\.

0.63

 peindre

0.52

ChildIndex

0.48

lük

0.47

 nothing

0.47

 teater

0.47

 aikana

0.46

glGet

0.46

 notwithstanding

0.46

 excuse

0.46

Activations Density 0.060%

numerical values, particularly measurements and statistics

No Comments

No Known Activations