INDEX

Explanations

mathematical terms and symbols related to equations and formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

homonymie

-0.78

setVerticalGroup

-0.72

writeFieldEnd

-0.71

 AssemblyProduct

-0.71

 initComponents

-0.70

ImageContext

-0.70

 nahilalakip

-0.70

EndContext

-0.69

CloseOperation

-0.68

XmlAccessType

-0.67

POSITIVE LOGITS

{~

0.66

Mi

0.51

↵

0.48

 compro

0.48

与其

0.47

 facts

0.46

0.45

mi

0.45

 dónde

0.45

Be

0.44

Activations Density 0.267%

mathematical terms and symbols related to equations and formulas

No Comments

No Known Activations