INDEX

Explanations

mathematical notation and expressions, particularly those related to integrals and sums

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ThroughAttribute

-0.58

 faucet

-0.56

 betweenstory

-0.53

amante

-0.52

-0.50

 ResourceManager

-0.50

 stimmen

-0.49

kton

-0.49

 NavController

-0.48

formatics

-0.48

POSITIVE LOGITS

 CreateTagHelper

0.78

Jîn

0.71

 estekak

0.67

ffilm

0.66

toEqual

0.64

nloa

0.63

WriteTagHelper

0.61

(!__

0.61

 חיצוניים

0.60

GOTREF

0.60

Activations Density 0.151%

mathematical notation and expressions, particularly those related to integrals and sums

No Comments

No Known Activations